Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is an assignment/organization operation but doesn't clarify whether this creates new projects, modifies existing memory-project relationships, requires specific permissions, has side effects, or what happens on success/failure. For a tool that likely modifies data, this leaves significant behavioral questions unanswered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each earn their place. The first states the core action, the second provides usage context with helpful examples. No wasted words, well-structured, and front-loaded with the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which handles return values), 2 parameters with 0% schema coverage, and no annotations, the description provides adequate but incomplete context. It covers the basic purpose and usage but lacks behavioral details about this likely-mutating operation. The presence of an output schema prevents this from being a lower score.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage and only 2 parameters, the description adds meaningful context beyond the bare schema. It clarifies that 'project' represents a project space for organization and provides concrete examples ('tessera', 'frontend-app', 'api-design'), though it doesn't explain the 'memory_id' parameter or format requirements for either parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('assign') and resource ('memory to a project space'), and provides concrete examples of project contexts. However, it doesn't explicitly differentiate this tool from potential sibling tools like 'memory_tags' or 'memory_categories' that might also organize memories, which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool ('to organize memories by project context') and provides helpful examples, but it doesn't explicitly state when NOT to use it or mention alternatives among the many sibling tools. The guidance is useful but incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It describes what the tool checks but lacks behavioral details such as whether it modifies files, requires specific permissions, outputs format, or handles errors. The description adds some context (e.g., what sprawl and consistency checks entail) but is insufficient for a mutation-like audit tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, with the first sentence covering the core purpose and checks. The second sentence details optional parameters efficiently. There is minimal waste, though it could be slightly more structured (e.g., bullet points for clarity).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, 0% schema coverage, but an output schema exists, the description is moderately complete. It covers purpose and parameter semantics but lacks behavioral transparency (e.g., mutation risks, output format). The output schema mitigates some gaps, but for an audit tool with potential file interactions, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the semantics of check_sprawl ('detect multiple versions of the same PRD') and check_consistency ('check cross-PRD consistency for period selectors and tiers'), adding meaningful context beyond the schema's basic titles. However, it does not clarify file_path usage (e.g., format, supported file types).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('audit', 'checks') and resources ('PRD file'), detailing what aspects are evaluated (quality, completeness, 13-section structure, coverage, Mermaid syntax, wireframes, versioning, changelog). It distinguishes from sibling tools by focusing on PRD-specific auditing rather than general document operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for auditing PRD files but does not explicitly state when to use this tool versus alternatives (e.g., other document-checking siblings like check_document_freshness or detect_contradictions). It mentions optional checks (sprawl, consistency) but lacks guidance on prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the tool's function and output but lacks details on permissions, rate limits, error handling, or whether it's read-only or mutative. For a tool with no annotations, this leaves significant gaps in understanding its operational behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and efficient, consisting of two sentences that directly convey purpose, output, and usage without any wasted words. Every sentence adds value, making it easy to parse and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (1 parameter, no annotations, but with an output schema), the description is reasonably complete. It covers purpose, output format, and usage context. Since an output schema exists, it doesn't need to detail return values, but it could benefit from more behavioral details given the lack of annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter with 0% description coverage, so the description must compensate. It implies the parameter's role by mentioning 'days since last update' and 'stale/outdated documents that haven't been modified recently', which adds semantic meaning to the 'days_threshold' parameter beyond the schema's basic type and default value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('check for stale/outdated documents') and resources ('documents'), distinguishing it from siblings like 'search_documents' or 'list_sources' by focusing on freshness rather than content or listing. It explicitly mentions the output format ('list grouped by project showing file names and days since last update'), which adds clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool ('proactively to suggest document reviews'), indicating its role in maintenance or review workflows. However, it does not explicitly state when not to use it or name alternatives among the many sibling tools, such as 'search_documents' for content-based queries, leaving some ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses key behaviors: retrieves memories and documents, assembles in priority order, and truncates to fit token budget. However, it lacks details on how retrieval works (e.g., sources, recency), what 'optimal' means, error handling, or performance characteristics like rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, followed by a usage guideline. Every word earns its place with no redundancy or fluff, making it highly efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (involves retrieval, assembly, truncation), no annotations, and an output schema (which handles return values), the description is reasonably complete. It covers the main workflow but could benefit from more behavioral details (e.g., retrieval methods, priority criteria). The output schema reduces the need to explain returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the overall function (build context window for query with token budget) but doesn't detail individual parameters. However, with only 3 parameters (query, token_budget, include_documents), the high-level context is sufficient for basic understanding, though specifics like default values or boolean effects are missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Build an optimal context window for a query within a token budget.' It specifies the action (build), resource (context window), and key constraints (token budget). However, it doesn't explicitly differentiate from sibling tools like 'recall', 'deep_recall', or 'unified_search', which might have overlapping retrieval functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for usage: 'Use this to prepare context for another AI tool.' This indicates it's a preparatory step rather than an end action. It doesn't specify when not to use it or name alternatives among siblings, but the guidance is practical and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the tool 'detects when you changed your mind about something', which hints at analytical behavior, but does not clarify output format, data sources, permissions required, or any limitations. This leaves significant gaps in understanding how the tool operates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, with two sentences that directly state the tool's function and an additional behavioral hint. There is no wasted text, and it efficiently communicates the core purpose without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there is an output schema (which handles return values), 0 parameters, and no annotations, the description is moderately complete. It explains what the tool does but lacks details on behavioral traits, usage context, or how it integrates with sibling tools. For a tool with analytical functions like detecting mind changes, more context would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, meaning no parameters are documented in the schema. The description does not add parameter information, but since there are no parameters, this is acceptable. The baseline for 0 parameters is 4, as the description need not compensate for missing parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Show decision timeline — how decisions evolved over time, grouped by topic.' It specifies the verb ('show'), resource ('decision timeline'), and scope ('grouped by topic'). However, it does not explicitly differentiate from sibling tools like 'extract_decisions' or 'detect_contradictions', which may have overlapping functions, so it falls short of a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions detecting when you changed your mind, but does not specify prerequisites, exclusions, or compare it to similar tools like 'extract_decisions' or 'detect_contradictions'. This lack of contextual usage information limits its effectiveness for an AI agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the tool 'decomposes the query into multiple perspectives and merges results' and that 'Each result includes a confidence verdict,' which adds some behavioral context. However, it lacks details on permissions, rate limits, error handling, or what 'confidence verdict' entails, leaving gaps for a tool with 5 parameters and an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, with the core purpose stated first. All sentences are relevant, explaining the method and usage. However, it could be slightly more structured by separating usage guidelines into a distinct part, but it's efficient with zero waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 parameters, no annotations, but with an output schema), the description is somewhat complete. It explains the purpose and method but lacks details on parameters, behavioral traits, and how the output schema relates. The output schema reduces the need to explain return values, but more context on usage and limitations would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It doesn't mention any parameters explicitly, such as 'query,' 'top_k,' or date filters. While it implies query usage through 'Search memories,' it adds no semantic details beyond what the schema titles provide. With 5 parameters and no schema descriptions, this is a minimal baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search memories using multiple query angles for better recall.' It specifies the verb ('search'), resource ('memories'), and method ('multiple query angles'). However, it doesn't explicitly distinguish it from sibling tools like 'recall' or 'deep_search' beyond mentioning 'Like deep_search but for memories,' which is somewhat helpful but not fully differentiating.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Use when recall misses relevant memories.' This indicates when to prefer this tool over alternatives like 'recall.' It also mentions 'Like deep_search but for memories,' hinting at a comparison. However, it doesn't explicitly state when not to use it or list all relevant alternatives, such as 'list_memories' or 'search_by_category.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: the tool decomposes queries into 2-4 perspectives (core keywords, individual terms, reversed emphasis), merges results, and includes verdicts (confident match, possible match, low relevance). This covers the search process and output format, though it lacks details on performance or limitations like rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by operational details and usage guidelines in three concise sentences. Every sentence adds value: the first defines the tool, the second explains its method and output, and the third specifies when to use it, with zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multi-angle search) and no annotations, the description does well by explaining the process and output verdicts. With an output schema present, it doesn't need to detail return values. It covers the 'what' and 'when' effectively, though it could add more on behavioral constraints like error handling or performance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter details. The description adds no explicit parameter semantics—it doesn't explain 'query', 'top_k', 'project', or 'doc_type'. However, the context of search is implied, and with an output schema present, some burden is reduced. Baseline 3 is appropriate as the description doesn't compensate for the coverage gap but doesn't mislead.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search documents using multiple query angles for better recall.' It specifies the verb ('search'), resource ('documents'), and distinct approach ('multiple query angles'), differentiating it from sibling tools like 'search_documents' or 'unified_search' by emphasizing decomposition into perspectives and merging results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides usage guidance: 'Use when standard search misses relevant results.' This directly tells the agent when to choose this tool over alternatives, such as 'search_documents' (implied as 'standard search'), making it clear for decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses behavioral traits: the tool finds conflicts, shows severity (HIGH/MEDIUM), and indicates which memory is newer. However, it lacks details on permissions, rate limits, or what 'stored memories' entail. The description adds value but doesn't fully compensate for the absence of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with three sentences: purpose, details, and usage guidance. Each sentence adds value without redundancy. It's front-loaded with the core function. Minor improvement could be made by tightening phrasing, but it's efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (moderate, as it analyzes contradictions), no annotations, an empty input schema, and an output schema (which handles return values), the description is reasonably complete. It covers purpose, behavior, and usage, though it could elaborate more on scope or limitations. The output schema reduces the need for return value details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are 0 parameters, and schema description coverage is 100%, so the baseline is high. The description doesn't need to explain parameters, but it implies the tool operates on all stored memories without filtering. This adds slight context beyond the empty schema, justifying a score above the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Detect contradictions among your stored memories' with specific examples (decisions, preferences, facts). It distinguishes itself from siblings by focusing on contradiction detection rather than listing, searching, or managing memories. However, it doesn't explicitly contrast with tools like 'audit_prd' or 'suggest_cleanup' that might involve consistency checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for usage: 'Use periodically to keep your knowledge base consistent,' implying it's a maintenance tool. It doesn't specify when not to use it or name alternatives, but the periodic guidance is helpful. No explicit exclusions or comparisons to siblings like 'audit_prd' are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions automatic saving and extraction scope, but lacks details on permissions needed, rate limits, error conditions, or what 'save them as memories' entails operationally. For a tool that modifies memory state, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise and front-loaded. The first sentence establishes the core purpose, the second provides primary usage timing, and the third adds parameter context. Every sentence earns its place with no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (memory creation/updating), no annotations, and the presence of an output schema, the description covers purpose and usage well but lacks behavioral details about the mutation operation. The output schema reduces the need to describe return values, but more transparency about the write operation would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaningful context for the single parameter: 'You can also pass a summary text to extract facts from.' This explains the optional 'summary' parameter's purpose beyond the schema's basic type information. With 0% schema description coverage and only one parameter, the description effectively compensates by clarifying when and why to use this parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('digest', 'extract', 'save') and resources ('conversation', 'decisions, preferences, and facts', 'memories'). It distinguishes from siblings like 'extract_decisions' by covering broader extraction and automatic saving, and from 'remember' by focusing on session-level digestion rather than general memory creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidelines: 'Call this at the end of a conversation to preserve important knowledge.' It also offers an alternative usage scenario: 'You can also pass a summary text to extract facts from.' This clearly indicates when and how to use the tool versus other memory-related siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool returns specific outputs (related documents, shared topics, Mermaid subgraph), which is helpful, but lacks details on permissions, rate limits, side effects, or error conditions. For a tool that likely queries a knowledge graph, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the core functionality and output. It's front-loaded with the main action and resource, with no wasted words or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which should document return values), the description adequately covers the basic purpose and output types. However, with no annotations and 0% schema description coverage, it could benefit from more behavioral context and parameter guidance to be fully complete for a knowledge graph query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the lack of parameter documentation in the schema. The description implies 'query' is used to specify the document or concept, but doesn't explain format or constraints. It doesn't mention 'top_k' at all. This provides minimal semantic value beyond the schema's basic structure, meeting the baseline for partial compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Show connections') and resource ('specific document or concept in the knowledge graph'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'find_similar', 'topic_map', or 'knowledge_graph' that might also explore relationships, so it doesn't reach the highest score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'find_similar' or 'topic_map'. It mentions the output includes 'related documents, shared topics, and a focused Mermaid subgraph', but this doesn't help the agent decide when this tool is appropriate compared to other exploration tools in the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions the tool exports memories for AI platform use, which implies read-only behavior, but doesn't specify permissions needed, rate limits, or what exactly gets exported (e.g., format details, scope). It adds some context about migration purpose but lacks comprehensive behavioral details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with zero waste: the first explains what the tool does and lists targets, the second provides clear usage guidance. It's appropriately sized and front-loaded with essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 1 parameter with low schema coverage and an output schema present, the description is reasonably complete. It covers purpose, usage, and parameter meaning, but lacks details on behavioral aspects like permissions or export scope. The output schema likely handles return values, so the description doesn't need to explain those.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter with 0% description coverage. The description compensates by explaining the 'target' parameter's purpose and listing the three supported values ('chatgpt', 'gemini', 'standard'), which adds meaningful semantics beyond the bare schema. However, it doesn't detail default behavior or format specifics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Export') and resource ('memories'), specifying it's for use in another AI tool. It distinguishes from siblings like 'export_knowledge' or 'export_memories' by focusing on AI platform migration formats rather than general exports.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool: 'Use this when migrating knowledge to another AI platform.' It provides clear alternatives by listing supported targets ('chatgpt', 'gemini', 'standard'), helping the agent choose the appropriate format for the specific migration scenario.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden but only covers format options and basic usage. It lacks details on permissions, rate limits, output behavior (though output schema exists), or whether this is a read-only or destructive operation, leaving significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by specific format details and a usage tip for 'obsidian'. Every sentence adds value without redundancy, making it efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 1 parameter with no schema descriptions and an output schema present, the description adequately covers parameter semantics and tool purpose. However, it lacks behavioral details like authentication or side effects, which are important for a tool that exports data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, but the description compensates by explaining the 'format' parameter's semantics, listing supported formats and their purposes. It adds meaningful context beyond the bare schema, though it could detail default behavior more explicitly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Export all your knowledge') and resource ('knowledge'), distinguishing it from siblings like 'export_memories' or 'export_for_ai' by specifying comprehensive export of all knowledge rather than subsets or specialized formats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context on when to use specific formats (e.g., 'obsidian' for Obsidian vaults), but does not explicitly state when not to use this tool versus alternatives like 'export_memories' or 'export_for_ai', leaving some ambiguity about tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool returns a JSON string with all memories and metadata, which is useful behavioral context. However, it lacks details on potential side effects, permissions needed, or performance considerations like data size or timeouts, leaving some gaps in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences that are front-loaded with the core action and purpose, followed by output details. Every word adds value without redundancy, making it highly efficient and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no annotations, but has an output schema), the description is complete. It explains what the tool does, its purpose, and the return format, which aligns with the output schema. No additional information is needed for effective use in this context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately adds no parameter details, focusing instead on the tool's purpose and output. This meets the baseline for zero parameters, but a perfect score would require explicit mention of the lack of parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Export') and resource ('all saved memories'), and distinguishes it from siblings like 'list_memories' by specifying the output format and purpose ('as JSON for backup or transfer'). It provides a complete picture of what the tool does beyond just listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the purpose ('for backup or transfer'), which gives clear context for when to use this tool. However, it does not mention when not to use it or name specific alternatives among siblings, such as 'export_for_ai' or 'export_knowledge', which could provide more precise guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'extract' and 'call automatically,' but doesn't disclose behavioral traits like permissions needed, rate limits, whether it's read-only or mutative, or what the extraction entails (e.g., format, scope). This is inadequate for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, front-loading the core purpose. However, the second sentence ('Call automatically...') is somewhat vague and could be more precise, slightly reducing efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, 0% schema coverage, but an output schema exists, the description is moderately complete. It states the purpose and basic usage but lacks details on parameters, behavioral traits, and differentiation from siblings. The output schema helps, but more context is needed for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds no information about parameters like 'project_id' or 'since'—not explaining what they mean, how they affect extraction, or their optional nature. With 2 parameters and no schema descriptions, this leaves semantics unclear.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Extract decisions from session logs and decision logs.' It specifies the verb ('extract') and resources ('session logs and decision logs'), making it easy to understand what the tool does. However, it doesn't differentiate from sibling tools like 'decision_timeline' or 'recall', which might have overlapping functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides minimal guidance: 'Call automatically when asked about past decisions.' This implies usage context but lacks explicit when-to-use vs. alternatives, prerequisites, or exclusions. No comparison to siblings like 'decision_timeline' or 'recall' is made, leaving gaps in selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool returns 'related documents ranked by similarity,' which is helpful, but lacks critical details: it doesn't specify what similarity metric is used, whether results are paginated, if there are rate limits, or what authentication/permissions are required. For a tool with no annotation coverage, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded: two sentences with zero wasted words. The first sentence states the purpose and outcome, and the second provides usage guidance. Every sentence earns its place by adding distinct value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists (which likely defines the return structure), the description doesn't need to detail return values. However, with no annotations, 2 parameters (one required), and 0% schema coverage, the description is incomplete: it lacks parameter semantics, behavioral details like error handling, and differentiation from siblings. It's minimally adequate but has clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning parameter titles ('Source Path', 'Top K') provide minimal semantic information. The description adds no parameter-specific details—it doesn't explain what 'source_path' should contain (e.g., file path, document ID) or how 'top_k' affects results beyond the default. With low schema coverage, the description fails to compensate, leaving parameters largely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Find documents similar to a given document. Returns related documents ranked by similarity.' It specifies the verb ('find'), resource ('documents'), and outcome ('ranked by similarity'). However, it doesn't explicitly differentiate from sibling tools like 'search_documents' or 'explore_connections' that might also find related content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: 'Use this when users ask 'what else is related to this document'.' This gives a clear context for when to invoke the tool. However, it doesn't mention when NOT to use it or name specific alternatives among the many sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions deletion behavior but lacks details on permissions, confirmation, reversibility, or error handling. The description adds minimal behavioral context beyond the basic destructive action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste - first states purpose, second provides usage guidance. Every word serves a clear function, and the information is front-loaded appropriately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations and 1 parameter, the description covers basic purpose and usage but lacks details on permissions, side effects, or error cases. The existence of an output schema helps, but more behavioral context would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by explaining the parameter meaning ('filename without .md extension'), adding value beyond the bare schema. However, it doesn't provide format examples or constraints, leaving some ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Delete a specific memory') and resource ('by filename'), distinguishing it from sibling tools like list_memories or export_memories. It uses precise language that leaves no ambiguity about the tool's function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly provides when to use this tool ('Delete a specific memory') and includes a prerequisite step ('Use list_memories first to find the memory to delete'), offering clear guidance on proper usage sequence without alternatives needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool 'checks' various aspects and 'returns actionable recommendations', but does not specify whether it performs read-only operations, requires permissions, has side effects, or details rate limits or performance impacts. This leaves significant gaps for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise and well-structured, consisting of a single sentence that efficiently conveys the tool's function, scope, and output. Every word earns its place, with no wasted information, making it easy to understand at a glance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 0 parameters, 100% schema coverage, and an output schema exists, the description does not need to explain inputs or return values. However, as a diagnostic tool with no annotations, it lacks details on behavioral aspects like execution time, error handling, or integration with sibling tools, leaving some contextual gaps despite the structured data support.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the inputs. The description does not need to add parameter information, and it appropriately focuses on the tool's purpose and output without redundant details, earning a baseline score of 4 for zero-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as running a comprehensive health check on the Tessera workspace, specifying what it checks (config validity, dependencies, index status, stale documents, zero-result query patterns) and what it returns (actionable recommendations). However, it does not explicitly differentiate from sibling tools like 'tessera_status' or 'memory_health', which might have overlapping functions, so it lacks sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, timing, or exclusions, and with many sibling tools (e.g., 'tessera_status', 'memory_health', 'project_status'), there is no indication of how this tool differs in usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool extracts decisions, preferences, and facts, which adds behavioral context beyond basic import functionality. However, it lacks details on permissions, rate limits, error handling, or what happens to the imported data (e.g., storage location, indexing).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by usage instructions and benefits. Every sentence earns its place: the first defines the action, the second explains parameters, the third describes processing, and the fourth states the use case. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (importing and processing external data), no annotations, and the presence of an output schema, the description is mostly complete. It covers purpose, parameters, and processing outcome, but could benefit from mentioning authentication needs, data limits, or output format since the output schema is not described here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by explaining both parameters: 'data' as 'exported JSON data' to paste and 'source' with enumerated values ('chatgpt', 'claude', 'gemini', 'text'). This adds meaningful semantics beyond the bare schema, though it could specify JSON structure or validation rules.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('import', 'extracts') and resources ('conversations from ChatGPT, Claude, or Gemini exports'). It distinguishes from siblings by focusing on importing external conversation data, unlike tools like 'import_memories' or 'import_from_ai' which may handle different data types or sources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('to recover knowledge from past AI interactions') and specifies the supported sources. However, it does not explicitly state when NOT to use it or mention alternatives like 'import_memories' or 'import_from_ai' for comparison.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions that 'memories will be automatically categorized and stored in Tessera', which adds some behavioral context about the outcome. However, it lacks details on permissions, error handling, rate limits, or what happens if the data format is invalid, leaving significant gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the action, parameters, and outcome without any wasted words. It is front-loaded with the core purpose and includes essential details concisely.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there is an output schema (which reduces the need to describe return values) but no annotations and low schema coverage, the description is moderately complete. It covers the basic operation and parameters but lacks depth on behavioral aspects like error handling or side effects, which are important for an import tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaning by explaining that 'data' should be 'exported JSON data' and 'source' specifies the AI tool, which clarifies the parameters beyond the schema. However, it doesn't detail the JSON structure, validation rules, or default behavior for 'source', leaving some ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('import') and resource ('memories') with the source ('from another AI tool'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like 'import_memories' or 'import_conversations', which might handle similar imports but from different sources or formats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by specifying the source options ('chatgpt', 'gemini', or 'standard'), but it doesn't provide explicit guidance on when to use this tool versus alternatives like 'import_memories' or 'import_conversations'. No exclusions or prerequisites are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'batch import' and references an export tool for format, but lacks critical details: whether this operation overwrites existing memories, requires specific permissions, has rate limits, or what happens on success/failure. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise and front-loaded, consisting of two sentences that directly convey the tool's purpose and usage without any wasted words. Every sentence earns its place by providing essential information about the operation and format reference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which reduces the need to describe return values) but no annotations and low schema coverage, the description is moderately complete. It covers the basic purpose and format, but lacks details on behavioral traits, error handling, and parameter semantics, making it adequate but with clear gaps for a mutation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter with 0% description coverage, so the description must compensate. It adds value by specifying the parameter 'data' should be a JSON string in a particular format and referencing 'export_memories' for examples. However, it doesn't explain the semantics of fields like 'content', 'tags', or 'source', or provide validation rules, leaving gaps in understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Import memories from a JSON string (batch import).' It specifies the verb ('import'), resource ('memories'), and scope ('batch import'), distinguishing it from sibling tools like 'export_memories' or 'list_memories'. However, it doesn't explicitly differentiate from 'import_conversations' or 'import_from_ai', which are similar import operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool by referencing 'export_memories to get the expected format,' indicating it's for batch imports of memories in a specific JSON structure. It implies usage for data migration or restoration scenarios. However, it doesn't explicitly state when not to use it or compare it to alternatives like 'import_conversations'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses that this is a potentially heavy operation ('rebuild the entire index from scratch') and mentions optional directory filtering. However, it lacks details on permissions needed, rate limits, whether it's destructive to existing data, or expected runtime/confirmation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with zero waste: first states core purpose, second gives usage guidelines, third explains parameter usage. Front-loaded with the main action, each sentence earns its place by adding distinct value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 1 parameter with no schema descriptions but an output schema exists, the description is reasonably complete. It covers purpose, usage, and parameter intent. However, as a tool that likely performs significant processing, more behavioral context (e.g., idempotency, side effects) would enhance completeness, though the output schema may cover return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Parameter count is 1 with 0% schema description coverage. The description adds meaningful semantics: 'Optionally pass specific directory paths to index only those,' explaining that 'paths' parameter controls scoping (full vs. partial indexing). This compensates well for the lack of schema descriptions, though it doesn't specify path format or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('index or re-index') and resource ('all workspace documents into the vector store'), specifying it's for Tessera. It distinguishes from siblings like 'sync_documents' or 'search_documents' by emphasizing full workspace indexing rather than incremental sync or search operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'when setting up Tessera for the first time, or when you want to rebuild the entire index from scratch.' Also mentions an alternative usage pattern: 'Optionally pass specific directory paths to index only those,' providing clear context for partial vs. full indexing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the output format ('Mermaid diagram') and default values for parameters, but lacks details on permissions, rate limits, error conditions, or how the graph is generated (e.g., algorithm, data sources). This is a significant gap for a tool with complex functionality.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence, followed by parameter details in a concise list. Every sentence adds value without redundancy, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (building knowledge graphs) and the presence of an output schema (which handles return values), the description is moderately complete. It covers purpose and some parameters but lacks behavioral details like permissions or limitations, which are critical for such a tool. With no annotations, this leaves gaps in understanding how to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaningful context for 'scope' (explaining 'project' vs. 'all') and 'max_nodes' (default and purpose), but does not cover 'query' or 'project' parameters. Since 2 out of 4 parameters are explained, this partially compensates for the schema gap, though not fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('Build a knowledge graph') and resources ('from indexed documents'), specifying what it shows ('relationships between concepts, decisions, and entities') and what it returns ('a Mermaid diagram of the document relationships'). It distinguishes itself from sibling tools like 'topic_map' or 'explore_connections' by focusing on document-based relationship visualization.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through the mention of 'scope' (project vs. all) and 'max_nodes', suggesting when to adjust parameters, but does not explicitly state when to use this tool versus alternatives like 'topic_map' or 'explore_connections'. No prerequisites or exclusions are provided, leaving usage context somewhat vague.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what data is retrieved (statistics like total memories, category breakdown) but lacks details on permissions required, rate limits, response format, or potential side effects. For a read-only tool with zero annotation coverage, this leaves significant gaps in understanding its operational behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, with two sentences that efficiently convey the tool's purpose and scope. Every sentence adds value: the first lists specific statistics, and the second provides context as a dashboard overview. There is no redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (a read-only statistical summary with 0 parameters), the description is reasonably complete. It outlines the types of statistics returned, and since an output schema exists, it does not need to detail return values. However, without annotations, it could benefit from more behavioral context, such as data freshness or access constraints, to fully inform usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the inputs. The description does not need to add parameter semantics, and it appropriately avoids discussing parameters, focusing instead on the output scope. This meets the baseline expectation for a parameterless tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('knowledge statistics'), listing concrete metrics like total memories, category breakdown, tag distribution, growth by month, and date range. However, it does not explicitly distinguish this from sibling tools like 'provenance_stats' or 'memory_health', which might also provide statistical insights, leaving some ambiguity in differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions 'A dashboard overview of everything Tessera knows,' which implies a broad summary context, but does not specify prerequisites, exclusions, or compare it to other tools like 'provenance_stats' or 'search_analytics' that might offer overlapping or complementary functionality.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions that knowledge is 'immediately indexed for search', which is useful behavioral context. However, it doesn't address important aspects like whether this is a write operation (implied but not stated), what permissions are needed, whether there are rate limits, what happens on duplicate content, or what the indexing process entails. For a tool that presumably modifies persistent storage, this is inadequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each earn their place. The first sentence states the core functionality, and the second provides usage context. There's zero wasted language, and the information is front-loaded appropriately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema (which reduces the need to describe return values), no annotations, and relatively simple parameters. The description covers the basic purpose and usage context adequately but lacks important behavioral details for a write operation and provides no parameter guidance. Given the output schema exists, the description is minimally complete but could be significantly improved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter documentation. The description doesn't mention any parameters at all, failing to explain what 'content', 'tags', or 'source' should contain or their significance. However, with only 3 parameters and one required, the baseline is 3 since the tool is relatively simple despite the lack of parameter guidance in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('save new knowledge', 'index it for search') and identifies the resource ('knowledge'). It distinguishes from siblings by focusing on immediate indexing of discovered insights, unlike tools like 'remember' or 'list_memories'. However, it doesn't explicitly contrast with all similar tools like 'import_memories' or 'ingest_documents'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool ('to capture insights, patterns, or facts discovered during conversation'), which helps differentiate it from bulk import or search tools. It doesn't explicitly state when NOT to use it or name specific alternatives, but the context is sufficiently clear for typical usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. While it mentions 'optional filtering' and 'browse across sessions', it doesn't address key aspects like whether this is a read-only operation, pagination behavior (implied by the 'limit' parameter but not explained), rate limits, authentication requirements, or what constitutes a 'memory' in this context. The description provides minimal behavioral context beyond the basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with two sentences that are front-loaded with the core purpose. Every word earns its place: the first sentence states what the tool does, and the second provides usage context without redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there's an output schema (which handles return values), no annotations, and low schema coverage for the single parameter, the description is moderately complete. It covers the basic purpose and usage but lacks details on filtering mechanics, behavioral traits, and parameter specifics. For a tool with one parameter and output schema, it's adequate but has clear gaps in guidance and transparency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions 'optional filtering' but doesn't specify what filtering options exist or how they work. The input schema has one parameter ('limit') with 0% schema description coverage, and the description doesn't explain what 'limit' controls or its default value. Since schema coverage is low, the description should compensate more for parameter semantics but only adds vague context about filtering.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'List saved memories with optional filtering' specifies the verb (list) and resource (memories), and 'browse what Tessera has remembered across sessions' adds helpful context about scope. However, it doesn't explicitly differentiate from sibling tools like 'recall', 'deep_recall', or 'unified_search', which may also involve memory retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage guidance with 'Use to browse what Tessera has remembered across sessions', suggesting this is for general browsing rather than targeted recall. However, it doesn't explicitly state when to use this tool versus alternatives like 'recall' or 'search_by_tag', nor does it mention any prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool does (listing hooks and their details) and hints at configuration context, but does not disclose traits like whether it requires specific permissions, has rate limits, or what the output format entails. It adds some value but lacks comprehensive behavioral details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence, followed by additional details in a second sentence. Both sentences earn their place by providing essential information without waste, making it efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (simple listing with no parameters) and the presence of an output schema (which likely covers return values), the description is mostly complete. It explains what the tool does and provides configuration context, but could benefit from more behavioral transparency, such as permissions or output specifics, to be fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%, so the baseline is 4. The description does not need to add parameter information, as there are none to document, and it appropriately focuses on the tool's function without redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('List') and resource ('all registered plugin hooks'), and distinguishes it from sibling tools by specifying what it shows ('which events have hooks attached and what scripts/functions will be called'). It avoids tautology by not merely repeating the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('List all registered plugin hooks') and includes a configuration note ('Configure hooks in workspace.yaml under 'hooks:' section'), which implies usage for setup or verification. However, it does not explicitly state when not to use it or name alternatives among siblings, such as for managing hooks versus listing them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it describes what information is returned, it doesn't address important behavioral aspects like whether this is a read-only operation, if there are rate limits, how results are sorted or paginated, or what permissions might be required. The description only covers output content, not operational behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each add value. The first sentence specifies exactly what the tool returns, and the second provides higher-level context about knowledge distribution. There's no wasted language or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that the tool has 0 parameters, 100% schema coverage, and an output schema exists, the description provides good contextual completeness. It explains what information is returned and the purpose of that information. The main gap is lack of behavioral context, but with an output schema handling return values, the description focuses appropriately on the 'why' rather than the 'what' of outputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, and instead focuses on what the tool returns, which is valuable context for a parameterless operation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and resource 'project spaces' with specific details about what information is included (memory counts, latest activity, top tags). It distinguishes the tool's purpose well, though it doesn't explicitly differentiate from potential sibling tools like 'project_status' or 'knowledge_stats' that might provide related information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With siblings like 'project_status', 'knowledge_stats', and 'list_sources' available, there's no indication of when this specific listing tool is appropriate versus other project or knowledge-related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. 'List all indexed source files' implies a read-only operation but doesn't specify format, pagination, sorting, or what 'indexed' means operationally. For a tool with zero annotation coverage, this leaves significant behavioral questions unanswered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a simple listing tool and front-loads the essential information without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 0 parameters, 100% schema coverage, and an output schema exists, the description is reasonably complete for its complexity level. However, with no annotations and many similar sibling tools, it could benefit from slightly more context about what constitutes 'indexed source files' versus other document types in the system.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the absence of parameters. The description appropriately doesn't waste space discussing parameters that don't exist, earning a baseline 4 for parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and resource ('all indexed source files'), providing specific verb+resource. However, it doesn't differentiate from sibling tools like 'list_memories', 'list_projects', or 'list_plugin_hooks', which follow similar naming patterns for different resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With many sibling tools like 'search_documents', 'unified_search', and 'find_similar' that might retrieve source-related information, there's no indication of when this specific listing tool is appropriate versus those search/filtering tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that categories are auto-detected and lists the specific types (decision, preference, fact, reference, context), which is useful behavioral context. However, it doesn't mention output format, pagination, sorting, or any limitations like rate limits or permissions required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose and key details (auto-detected categories). It's front-loaded with the main action and includes no redundant information, making it appropriately sized for a zero-parameter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, output schema exists), the description is reasonably complete. It explains what the tool does and the nature of the categories. With an output schema present, the description doesn't need to detail return values, and the lack of annotations is less critical for this read-only listing operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%. The description appropriately doesn't discuss parameters, as none exist. This meets the baseline for tools with no parameters, where minimal discussion is expected.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('memory categories'), and specifies that counts are included. It distinguishes this from other memory-related tools by focusing on categories rather than individual memories or searches. However, it doesn't explicitly differentiate from all sibling tools like 'memory_tags' or 'search_by_category'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention when this tool is appropriate compared to similar tools like 'memory_tags', 'search_by_category', or 'knowledge_stats', nor does it specify prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it analyzes based on specific criteria (repetition, source diversity, recency, category stability) and returns categorized results (high-confidence vs. low-confidence memories). However, it omits details like rate limits or authentication needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence and efficiently adds details in the second. Every sentence earns its place by clarifying the analysis method and output, with zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (analyzing multiple confidence factors), no annotations, and the presence of an output schema (which handles return values), the description is complete enough. It covers the purpose, methodology, and output categories without needing to detail parameters or return formats.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so no parameter information is needed. The description adds value by explaining the analysis criteria and output categories, justifying a score above the baseline of 3 for such cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('analyze confidence scores', 'rates each memory') and resources ('all memories'), distinguishing it from siblings like 'list_memories' or 'memory_health' by focusing on confidence evaluation rather than listing or health metrics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for analyzing memory confidence but does not explicitly state when to use this tool versus alternatives like 'audit_prd' or 'detect_contradictions'. It provides some context (e.g., 'may need review') but lacks clear exclusions or named alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the analysis behavior and output structure, but lacks details on permissions needed, rate limits, whether it's read-only or mutative, or any side effects. For a tool with no annotations, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence that efficiently covers purpose, classification, and outputs without waste. It's front-loaded with the core function ('Analyze memory health') and uses clear, structured language.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 0 parameters, 100% schema coverage, and an output schema (implied by 'Has output schema: true'), the description is mostly complete. It outlines the analysis scope and return values, though it could benefit from more behavioral context (e.g., read-only vs. mutative) to compensate for lack of annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description doesn't add param info, but that's appropriate here. Baseline is 4 for zero parameters, as it avoids redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Analyze memory health' with specific classification criteria (healthy, stale, orphaned) and output components (health score, breakdown, recommendations, growth statistics). It distinguishes from siblings like 'health_check' (generic) and 'suggest_cleanup' (focused on cleanup only) by specifying memory-specific analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives is provided. It doesn't mention when to choose it over 'health_check' (general health) or 'suggest_cleanup' (cleanup-focused), nor does it specify prerequisites or exclusions. Usage is implied through its description but not articulated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool does but lacks details on permissions, rate limits, response format, or potential side effects, which are critical for a tool that traces data lineage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the key action ('trace the provenance lineage') and details without any wasted words, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (tracing lineage), no annotations, and an output schema present, the description is minimally adequate. It explains the purpose but lacks behavioral and usage details that would help the agent operate it effectively in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, but the description compensates by implying the 'memory_id' parameter is used to trace lineage. Since there is only one parameter, the baseline is 4, as the description adds meaningful context beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('trace', 'created', 'derived') and resources ('provenance lineage of a memory'), distinguishing it from siblings like 'list_memories' or 'memory_confidence' by focusing on lineage tracing rather than listing or assessing memories.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or compare to similar tools like 'provenance_stats' or 'session_interactions', leaving the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but provides minimal behavioral disclosure. It mentions the tool lists tags with counts, but doesn't describe format, ordering, pagination, permissions needed, or whether this is a read-only operation (though implied by 'List'). For a tool with zero annotation coverage, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with zero waste. First sentence states purpose and scope, second provides usage context. Every word earns its place, and the most important information (what the tool does) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has zero parameters, 100% schema coverage, and an output schema exists (so return values are documented elsewhere), the description is reasonably complete. However, for a tool with no annotations, it should provide more behavioral context about what 'List' entails (format, limitations, etc.) to be fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and schema description coverage is 100% (empty schema is fully described). The description appropriately doesn't discuss parameters since none exist. Baseline for zero parameters with complete schema coverage is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('List all unique tags'), the resource ('across saved memories'), and includes additional context ('with their counts'). It distinguishes this tool from siblings like 'search_by_tag' (which likely filters memories by tag) and 'memory_categories' (which might handle different categorization).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('Useful for browsing memory categories'), indicating it's for exploratory analysis rather than targeted search. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the many sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: creates a backup before migration (safety measure), supports dry-run mode for previewing changes, and handles specific version upgrades. However, it doesn't mention potential risks, time requirements, or authentication needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly front-loaded with the core purpose in the first sentence, followed by important behavioral details and usage guidance. Every sentence earns its place: backup creation, dry-run usage, and version scope are all essential information with zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that this is a potentially destructive migration tool with no annotations but with an output schema, the description provides good coverage of purpose, behavior, and parameter usage. It could be more complete by mentioning authentication requirements or potential data loss risks, but the presence of an output schema means return values are documented elsewhere.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage for the single parameter, the description fully compensates by explaining the purpose and usage of the 'dry_run' parameter: 'Use dry_run=True to preview changes.' This adds crucial semantic meaning beyond the bare schema. The description doesn't mention default values or other parameter details, but with only one parameter, this is sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Migrate Tessera data'), target resource ('latest schema version'), and scope ('v0.6.x through v1.0.0 data format upgrades'). It distinguishes itself from siblings by focusing on data migration rather than search, import/export, or status operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides when-to-use guidance: 'Use dry_run=True to preview changes' indicates an alternative mode of operation. It also implies when to use this tool (for schema upgrades) versus other tools that handle different operations like import/export or search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the prerequisite workflow (call suggest_cleanup first) and need for user confirmation, which are important behavioral constraints. However, it doesn't describe what 'organize' actually does for each action type, potential side effects, error conditions, or authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with two sentences. The first sentence states the purpose and action types, while the second provides critical usage guidelines. No wasted words, though it could be slightly more structured by separating action types from the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters with 0% schema coverage and no annotations, the description is incomplete. It explains the workflow prerequisites well but doesn't cover parameter meanings, return values (though output schema exists), or the actual behavior of different actions. For a multi-action file manipulation tool, this leaves significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only mentions the 'action' parameter with its possible values, leaving 4 other parameters (path, destination, new_name, recursive) completely unexplained. The description adds minimal value beyond what the bare schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Organize files in the workspace' with specific actions listed ('move', 'archive', 'rename', 'list'). It distinguishes itself from sibling tools like 'suggest_cleanup' by being the execution tool, but doesn't explicitly differentiate from other file-related tools like 'read_file' or 'view_file_full'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: 'Always call suggest_cleanup first and get user confirmation before organizing.' This gives clear prerequisites and when-not-to-use guidance (without prior cleanup suggestion and user confirmation). It also references the sibling tool 'suggest_cleanup' as an alternative/precursor.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool retrieves status information, implying a read-only operation, but does not specify behavioral traits like permissions needed, rate limits, or whether it's safe to call frequently. The description adds some context about what data is included but lacks details on how it behaves or any constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, consisting of two concise sentences that directly state the tool's purpose and usage guidelines without any wasted words. Every sentence earns its place by providing essential information efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which reduces the need to describe return values) and no annotations, the description covers the basic purpose and usage but lacks details on parameters and behavioral aspects. It is complete enough for a simple status retrieval tool but has gaps in parameter explanation and behavioral transparency, making it adequate but with clear room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter with 0% description coverage, and the tool description does not mention any parameters. Since schema coverage is low, the description does not compensate by explaining the 'project_id' parameter's purpose or usage. With no parameter information in the description, it meets the baseline for minimal viability but does not add value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific details: 'Get project status including HANDOFF.md, recent changes, and file statistics.' It specifies the verb 'Get' and the resource 'project status' along with the specific components retrieved. However, it does not explicitly differentiate from sibling tools like 'list_projects' or 'project_status' alternatives, keeping it from a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Call automatically when asked about project status.' This gives explicit guidance on when to use the tool, indicating it's triggered by user inquiries about project status. However, it does not mention when not to use it or name specific alternatives among siblings, such as 'list_projects' for listing projects without detailed status.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it implies a read-only operation ('Get'), it lacks details on permissions, rate limits, response format, or potential side effects, which is inadequate for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose ('Get aggregate provenance statistics') and elaborates with specific details, with no wasted words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (statistical aggregation), no annotations, and an output schema (which handles return values), the description is partially complete. It specifies the statistics scope but lacks behavioral context like permissions or limitations, making it minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so no parameter information is needed. The description adds value by explaining what statistics are returned (e.g., 'breakdown by source type and session'), which goes beyond the empty input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('aggregate provenance statistics'), and it distinguishes itself from siblings by focusing on provenance-specific metrics (e.g., 'how many memories have provenance, breakdown by source type and session'), unlike tools like 'knowledge_stats' or 'memory_health'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or compare it to similar tools like 'knowledge_stats' or 'memory_health', leaving the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool reads files but doesn't mention permissions needed, error handling (e.g., for non-existent paths), output format, or any side effects. This leaves significant gaps in understanding how the tool behaves in practice.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core purpose and avoids unnecessary elaboration, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read operation with one parameter and an output schema (which handles return values), the description is minimally adequate. However, the lack of annotations and incomplete parameter guidance means it doesn't fully prepare an agent for real-world use, especially regarding error cases or permissions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds minimal value beyond the input schema, which has 0% description coverage. It clarifies that 'file_path' should be an absolute path, but doesn't explain path format, supported filesystems, or constraints. Given the low schema coverage, this partial compensation earns a baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Read file contents') and target resource ('by absolute path'), making the tool's purpose immediately understandable. It doesn't differentiate from sibling tools like 'view_file_full', but the verb+resource combination is specific enough for basic understanding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'view_file_full' (a sibling tool). There's no mention of prerequisites, limitations, or comparative context, leaving the agent with minimal usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the search functionality and filtering capabilities but doesn't mention important behavioral aspects like whether this is a read-only operation, what permissions are needed, how results are ranked, or what happens when no matches are found. The description adds some context but leaves significant behavioral questions unanswered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured with two sentences that each earn their place: the first establishes purpose and usage context, the second explains parameter capabilities. There's no wasted text, and the most important information (what the tool does and when to use it) comes first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, 1 required), no annotations, and the presence of an output schema, the description does a good job covering the essentials. It explains the core functionality, when to use it, and key parameter behaviors. The output schema means return values don't need explanation, but more behavioral context would improve completeness for a search tool with multiple filtering options.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates well by explaining the semantics of key parameters: it clarifies that 'since/until' are time filters using ISO dates and that 'category' accepts specific values (decision/preference/fact). However, it doesn't explain the 'query', 'top_k', or 'project' parameters, leaving some parameter semantics undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Search') and resource ('past memories from previous sessions'). It distinguishes from siblings by focusing on conversational memory recall rather than document search, analytics, or memory management operations present in the sibling list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance with concrete examples ('when the user asks 'what did I say about...', 'do you remember...', or references past conversations'). This gives clear context for when to invoke this tool versus alternatives like search_documents, deep_search, or unified_search from the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates this is a read-only operation ('View summary') but doesn't specify authentication requirements, rate limits, pagination behavior, or what happens when no sessions exist. The description is minimal and lacks important operational context that would help an agent use the tool effectively.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each earn their place. The first sentence states the core functionality, and the second provides valuable context about when the tool is useful. There's no wasted language or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simple nature (one optional parameter, output schema exists), the description is reasonably complete. The output schema will document return values, so the description doesn't need to explain them. However, for a tool with no annotations, more behavioral context would be beneficial to fully understand operational constraints and expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions no parameters, and the input schema has only one optional parameter ('limit') with 0% schema description coverage. Since there are effectively 0 parameters described in either the schema or description, the baseline score is 4. The description doesn't need to compensate for missing parameter documentation since no parameters are essential for tool operation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'View summary of recent sessions' with specific details about what information is provided (start time, end time, tool call count). It distinguishes itself from sibling tools by focusing on session summaries rather than memory management, document processing, or other functions. However, it doesn't explicitly differentiate from potential similar session-related tools like 'session_interactions' or 'session_prime'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage context by stating it's 'useful for understanding usage patterns over time,' suggesting when this tool would be appropriate. However, it doesn't explicitly state when to use this tool versus alternatives like 'session_interactions' or 'session_prime' (both sibling tools), nor does it mention any prerequisites or exclusions for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the tool's core function (saving for persistence) and typical use cases, but lacks details on implementation specifics like storage limits, retrieval mechanisms, error conditions, or authentication requirements. It adds basic context but leaves significant behavioral aspects undocumented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded: the first sentence states the core purpose, and the second provides usage guidelines. Both sentences earn their place with no wasted words, making it efficient and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (3 parameters, 1 required), no annotations, 0% schema coverage, but with an output schema present, the description is partially complete. It covers the 'what' and 'when' adequately but lacks details on parameters, behavioral constraints, and error handling. The output schema may help with return values, but the description doesn't fully compensate for the missing annotation and parameter documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter documentation. It doesn't mention any parameters explicitly, though it implies 'content' through 'piece of knowledge' and hints at organization through 'important decisions, preferences, or facts.' However, it doesn't explain the purpose of 'tags' or 'project' parameters, leaving them undocumented. The description adds minimal semantic value beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Save a piece of knowledge for cross-session persistence.' It specifies the verb ('save') and resource ('knowledge'), but doesn't explicitly differentiate it from sibling tools like 'learn' or 'recall' that might also handle knowledge storage or retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Use this when the user says 'remember this' or when important decisions, preferences, or facts should be preserved across conversations.' This gives specific triggers and scenarios, though it doesn't explicitly mention when NOT to use it or name alternatives like 'learn' or 'recall' from the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'shows' memories, implying a read-only operation, but doesn't clarify aspects like pagination, sorting, authentication needs, rate limits, or what 'recently' means. The description is minimal and lacks critical behavioral details for a tool with an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, consisting of two sentences that directly address the tool's purpose. There's no wasted language, though it could be more informative without sacrificing brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema, the description doesn't need to explain return values, but it lacks context for a read operation with one parameter. It specifies the memory sources but omits details like time frames or ordering, making it incomplete for guiding effective use despite the output schema's presence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter ('limit') with 0% description coverage, and the tool description adds no parameter information. Since there's only one parameter, the baseline is 4, but the description fails to explain what 'limit' controls (e.g., number of memories returned) or its impact, so it doesn't fully compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Review recently auto-learned memories' specifies the verb (review) and resource (memories), and 'Shows memories created by auto-extract, digest, or session summary' elaborates on the source of these memories. It distinguishes the tool from siblings like 'list_memories' by focusing on auto-learned content, though it doesn't explicitly contrast with all similar tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions the source of memories (auto-extract, digest, session summary) but doesn't specify contexts, prerequisites, or exclusions, nor does it reference sibling tools like 'list_memories' or 'deep_recall' for comparison.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool shows (analytics metrics) but doesn't disclose behavioral traits like whether it's read-only (implied by 'Show' but not explicit), authentication needs, rate limits, data freshness, or output format. For an analytics tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves operationally.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded: the first sentence clearly states the purpose and key metrics, and the second sentence provides usage guidance. Both sentences earn their place by adding value. It's efficient with zero waste, though it could be slightly more structured (e.g., separating purpose from parameters).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (analytics reporting), no annotations, 1 parameter with low schema coverage, but with an output schema present, the description is partially complete. It explains what the tool does and its use case, but lacks details on behavioral aspects (e.g., read-only nature, data scope) and parameter meaning. The output schema likely covers return values, so that gap is mitigated, but overall completeness is adequate with clear room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter ('days') with 0% schema description coverage (no description in schema). The tool description doesn't mention any parameters or add meaning beyond what the schema provides. With low schema coverage, the description fails to compensate by explaining the 'days' parameter's role (e.g., time range for analytics). However, since there's only 1 parameter, the baseline is slightly higher, but the lack of parameter semantics in the description limits its helpfulness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Show search usage analytics' followed by specific metrics (total queries, top queries, etc.). It uses a specific verb ('Show') and resource ('search usage analytics'), making the purpose explicit. However, it doesn't distinguish this from potential sibling tools like 'search_documents' or 'unified_search', which might also involve search functionality but serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage guidance: 'Use for understanding search patterns.' This gives context about when to use the tool (for analytics/insights into search behavior). However, it doesn't explicitly state when not to use it or name alternatives among the many sibling tools (e.g., how this differs from 'search_documents' or 'knowledge_stats'). The guidance is helpful but lacks specificity about tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions the need to check available categories first, which is useful context about prerequisites. However, it doesn't disclose behavioral traits like whether this is a read-only operation, what the search returns, performance characteristics, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each serve a clear purpose: the first states what the tool does, the second provides essential usage guidance. There's zero wasted text and it's front-loaded with the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there's an output schema (which handles return values), no annotations, and only one parameter with 0% schema coverage, the description provides basic but incomplete context. It covers the purpose and prerequisite, but lacks behavioral details about how the search works, what results to expect, or error handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter documentation. The description adds some semantic meaning by explaining that 'category' should be values like 'decision', 'preference', or 'fact', and references 'memory_categories' for available options. However, it doesn't fully document the parameter's format, constraints, or examples beyond the brief mention.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search memories by category' with examples of categories. It specifies the resource (memories) and action (search), but doesn't distinguish it from sibling tools like 'search_by_tag' or 'unified_search' beyond mentioning the category parameter.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: 'Use memory_categories first to see available categories.' This tells the agent when to use this tool (after checking categories) and references a specific sibling tool. However, it doesn't mention when NOT to use it or alternatives like 'search_by_tag' or 'unified_search'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the search functionality but lacks details on permissions, rate limits, output format, or error handling. For a search tool with no annotation coverage, this is a significant gap in transparency about how the tool behaves beyond its basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded: two sentences with zero waste. The first sentence states the core purpose, and the second provides essential usage guidance. Every word earns its place, making it easy to parse and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (1 parameter) and the presence of an output schema (which handles return values), the description is somewhat complete. It covers purpose and basic usage but lacks behavioral details like permissions or error handling. For a simple search tool, this is adequate but has clear gaps in transparency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter with 0% description coverage, so the description must compensate. It adds meaning by specifying that the 'tag' parameter is used to 'search memories by a specific tag,' which clarifies the parameter's role. However, it doesn't provide details on tag format, case sensitivity, or examples, leaving some ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search memories by a specific tag.' It specifies the verb ('Search') and resource ('memories'), and distinguishes the action (searching by tag) from general searching. However, it doesn't explicitly differentiate from sibling tools like 'search_by_category' or 'unified_search' beyond the tag focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage guidance: 'Use memory_tags first to see available tags.' This indicates a prerequisite step and suggests when to use this tool (after checking available tags). It doesn't explicitly state when not to use it or name alternatives, but the guidance is practical and context-aware.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions the hybrid search approach and filtering options but lacks critical behavioral details: it doesn't specify whether this is a read-only operation, what permissions are required, how results are returned (e.g., format, pagination), or any rate limits. For a search tool with no annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with two sentences: the first states purpose and usage guidance, the second details filtering options. It's front-loaded with key information and avoids unnecessary fluff, though it could be slightly more structured (e.g., bullet points for filters).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (search with 4 parameters), no annotations, and an output schema (which reduces need to explain returns), the description is partially complete. It covers purpose, usage, and some parameter semantics but lacks behavioral transparency details (e.g., safety, performance). The presence of an output schema helps, but gaps remain for adequate agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaning by explaining that 'project' filters by project ID and 'doc_type' filters by specific document types (prd, session_log, decision_log, document), which clarifies two of the four parameters. However, it doesn't explain 'query' (though it's self-evident) or 'top_k' (number of results), leaving some parameters inadequately documented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs 'Hybrid (semantic + keyword) search across indexed workspace documents' and lists specific document types (PRDs, decision logs, session logs, etc.). This provides a specific verb ('search') and resource ('indexed workspace documents'), though it doesn't explicitly differentiate from sibling tools like 'deep_search' or 'unified_search' beyond the hybrid approach mention.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states 'Call this tool first when the user asks about project-related content,' providing clear when-to-use guidance. It also mentions filtering capabilities (by project ID or doc_type), which helps define its scope relative to other search tools in the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool shows 'tool calls, queries, and results' but doesn't specify format, pagination behavior (despite a 'limit' parameter), whether it's read-only, or any performance characteristics. For a tool with 2 parameters and output schema, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured in two sentences: the first states the core functionality, the second adds the use case. There's no wasted text, and it's appropriately front-loaded with the main purpose. It could be slightly more concise by integrating the use case into the first sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (2 parameters, output schema exists), the description provides a clear purpose but lacks parameter explanations and detailed behavioral context. The existence of an output schema means the description doesn't need to explain return values, but it should still address how the tool behaves with its parameters. This is minimally adequate but has clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter descriptions. The tool description doesn't mention either parameter ('session_id' or 'limit'), so it adds no semantic information beyond what's inferred from the schema's property names and defaults. With 2 parameters completely undocumented, this meets the baseline for adequate but incomplete coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'View what happened in the current or past sessions' with specific details about what it shows ('tool calls, queries, and results'). It distinguishes itself from siblings like 'recent_sessions' by focusing on session content rather than session listings. However, it doesn't explicitly contrast with other content-review tools like 'digest_conversation' or 'decision_timeline'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage context ('useful for reviewing what was discussed and decided'), which suggests when to use it. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the many sibling tools. For example, it doesn't clarify whether this is better than 'digest_conversation' for certain review tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.