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

Describes the process (scans, chunks, ingests with embeddings) and dry-run mode. But lacks details on side effects (e.g., whether original memories are deleted), idempotency, and authorization requirements. With no annotations, the description should cover more behavioral traits.

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 relatively concise with four sentences, front-loaded with purpose. It covers key points without redundancy, though it could be slightly more streamlined.

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 tool with 5 parameters and no output schema, the description explains the overall workflow and use case. Lacks details on return format and partial failure behavior, but is reasonably complete for guiding an AI agent.

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 100%, so baseline is 3. Description adds context like 'dry-run mode to preview candidates' but does not significantly expand on parameter meanings beyond the schema. Adequate but not exceptional.

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 'promote' and the resources: from short-term memories (demo.memories) to permanent long-term storage (demo.marsvault_chunks). It distinguishes from siblings like 'demote_memory' by specifying automatic promotion of expiring 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?

Explicitly says 'Use this to prevent valuable context from being lost when short-term memories expire' and mentions dry-run mode for preview. However, it does not explicitly state when not to use it or compare to alternatives like manual insertion.

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. It clearly states the chunk is not deleted but flagged, and that it no longer appears in recall results. It also mentions optional traceability via 'superseded_by'. However, it does not detail reversibility or side effects on other functions, which would elevate transparency further.

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 three sentences with no filler. First sentence states action and resource, second explains the behavioral effect (flagging vs deletion), third gives usage context and mentions optional linking. Every sentence contributes 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 there is no output schema and the operation is simple (deprecation with side effect of hiding from recall), the description covers the main behavioral outcome. It could be slightly stronger by explicitly stating the reversal or persistence of the chunk, but it is sufficient for a straightforward 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 100%, so the schema already provides baseline meaning for each parameter. The description adds value by explaining the purpose of 'superseded_by' ('link to replacement chunk for traceability') and indicating that 'deprecated_at' defaults to now. This contextualizes the optional parameters 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 action ('deprecate'), the resource ('long-term memory chunk in demo.marsvault_chunks'), and distinguishes it from deletion by explaining it flags the chunk instead. This fully differentiates it from sibling tools like soft_forget or delete 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 explicit context for when to use this tool ('when information becomes incorrect, irrelevant, or is replaced by newer knowledge') and explains the core behavioral difference (not deleted, flagged). It lacks explicit 'when not to use' or alternative tool names, but the guidance is clear 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 provided, so description carries full behavioral burden. It discloses automatic chunking, vector embeddings, and permanent storage, but does not mention side effects, permissions, or idempotency. Adequate but not comprehensive.

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: first declares core action, second provides usage context. No filler, every sentence adds 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?

With 10 parameters and no output schema or annotations, description covers main purpose and chunking behavior. It could elaborate on chunk size or storage interaction, but schema handles param details. Adequate for the complexity.

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?

Input schema has 100% parameter coverage, so description adds context about chunking behavior (e.g., 'automatically split into semantically coherent chunks'). This complements the schema but does not deeply explain all parameters. Baseline 3 due to high schema 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?

Description clearly states it ingests a Hermes digest into long-term memory with chunking and embeddings. It provides usage examples like scheduled reports and daily digests, but does not explicitly distinguish from sibling tools like memory_ingest or insert_memory.

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 offers usage context ('scheduled reports, daily digests, or any structured summary content'), but lacks guidance on when not to use or alternatives. No explicit when-to-use vs. when-not-to-use.

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 explains that the tool returns provenance information (original source memory, session, tool, timeline) and implies a read-only operation. No contradictions.

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 long, front-loads the main action, and every sentence provides value without redundancy. It is concise and structured effectively.

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 one parameter and no output schema, the description fully covers its purpose, usage, and return values. It is complete for an AI agent to understand selection and invocation.

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 100% for the single parameter 'id', which is described as a UUID. The description elaborates on how this parameter relates to the tool's purpose, adding context 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 uses a specific verb 'trace' and clearly identifies the resource 'long-term memory chunk' and its provenance. It distinguishes from sibling tools which handle creation, deletion, or recall.

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 the tool: 'to understand why a piece of knowledge exists or to verify its reliability.' It does not provide explicit exclusions or alternatives, but the context of siblings implies when not to use.

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 provided; description implies it's a heavy operation ('use sparingly') but doesn't explicitly state read-only, auth needs, or 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?

Two concise sentences with no extraneous information; front-loaded with purpose and usage guidance.

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?

Adequately covers purpose, usage, and parameter for a simple fetch tool; lacks return format but no output schema expected.

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 fully describes the required 'id' parameter as UUID of the row, so description adds little beyond that.

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?

Clearly states it fetches complete text of a long-term memory chunk by ID, distinguishing itself from siblings like recall or get_summary.

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 advises to use sparingly and only after recall/get_summary when full entry is needed, indicating appropriate 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 the return size (~300 chars) and implies a safe, side-effect-free read operation. However, it doesn't explicitly state that it's read-only or other 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?

Two concise sentences with no wasted words. The first sentence defines the purpose, and the second provides usage guidance. Perfectly 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?

The tool is simple with one parameter, no output schema, and the description provides approximate output length and usage context. It references a sibling for complete text, making it complete for its low complexity.

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 100%, with the 'id' parameter described as 'UUID of the marsvault_chunks row' in the schema. The tool description adds no additional meaning beyond 'by ID', so it meets the baseline for high 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 it fetches a medium-length excerpt (~300 chars) of a long-term memory chunk by ID, using a specific verb 'Fetch' and resource 'excerpt'. This distinguishes it from the sibling 'get_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?

Explicitly says to use 'after recall when a preview match looks relevant' and provides a clear alternative: 'For complete text, call get_full.' This guides when to use and when not to.

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 provided, so description carries full burden. Discloses it is non-destructive (diagnostic) and outlines checks performed. Lacks specifics on output format or performance impact, but sufficient for understanding 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?

Two sentences: first defines what the tool does, second provides usage guidance. No redundant information. Every sentence adds value and 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 12 parameters with full schema descriptions and no output schema, the description adequately explains return values (chunk counts, expiring memories, gaps, conflicts). Could mention pagination or output format, but overall complete for a diagnostic 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 coverage is 100% with detailed parameter descriptions. Description adds no extra meaning beyond the schema; it focuses on tool purpose rather than parameter details. Baseline 3 is appropriate.

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?

Description clearly states 'Run comprehensive demo memory system diagnostics' and lists specific outputs (chunk counts, expiring memories, timeline gaps, conflicts). Differentiates from sibling tools like batch_promote, demote_memory, etc., which are operational rather than diagnostic.

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 recommends regular use for memory hygiene and before batch promotion. Context implies diagnostic use case. Does not explicitly discuss when not to use or alternative tools, but guidance is clear 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?

With no annotations provided, the description alone must disclose behavior. It reveals auto-expiration (7 days or custom), but does not mention idempotency, side effects, size limits, or what happens on insertion (e.g., duplicate handling). Adequate but not exhaustive.

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?

Four sentences, each adding value: purpose, use cases, default behavior, and alternative. Front-loaded with core action, no fluff. Ideal structure.

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?

No output schema exists, so description should explain what the tool returns (e.g., success indication, memory ID). It does not. Also missing details on error conditions or how inserted memories can be accessed later. Functional but incomplete for a 7-parameter 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 86%, so the schema already explains most parameters. The description adds minor context (e.g., body used for semantic search, agent_body defaults to server profile). This is baseline useful but not enhancing beyond 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: storing short-term demo memories with auto-expiration. It specifies the resource (demo.memories) and provides specific use cases (observations, decisions, session notes). This effectively distinguishes it from siblings like memory_ingest for permanent storage.

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 advises to use for ephemeral context, and explicitly names memory_ingest as the alternative for permanent knowledge. It also explains default expiration and custom expires_at. Could compare more broadly with other siblings, but key guidance is strong.

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 returns memory body, source, creation time, and expiration status, and that it orders reverse chronologically with an option to filter unexpired memories. While it doesn't mention mutability or idempotency, listing tools are inherently read-only; still, the description adds useful behavioral context beyond the 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 four sentences, each with a clear purpose: first defines the tool, second gives use cases, third distinguishes from alternatives, fourth lists return fields. No wasted words, front-loaded with key 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 no output schema, the description helpfully lists return fields. It explains ordering and filtering. However, it doesn't describe pagination or the exact behavior of 'limit' (e.g., max items), nor how 'source' filter interacts with the data. Still, it's fairly complete for a simple listing 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 coverage is 67% (limit and unexpired_only have descriptions). The tool description doesn't add extra meaning for parameters beyond what's in the schema, except it mentions 'expiration status' which relates to unexpired_only. It doesn't clarify how 'source' filter works but the enum values are self-explanatory. Adequate but doesn't significantly improve on 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 lists recent short-term memories in reverse chronological order, likening it to a daily log or activity feed. It distinguishes from siblings by specifying it's a time-ordered listing tool, not a semantic search tool (search_memories) or long-term retrieval (recall).

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: to review recent captures, check for duplicates before inserting, or browse recent activity. Also explicitly says when not to use and provides alternatives: 'not a search tool' – use search_memories for semantic search, use recall for long-term knowledge retrieval.

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?

Discloses key behaviors: automatically chunks input, generates vector embeddings, stores each segment. No annotations exist, so the description carries full burden and does well.

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 concise sentences, front-loaded with the core action. Every sentence adds value without 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 no output schema and 15 parameters with 100% schema coverage, the description covers the tool's purpose and process well. Could mention return value but not strictly necessary.

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 100%, so baseline is 3. The description adds minor extra context (e.g., 'Be specific and self-contained' for content) but does not significantly enhance 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?

Clearly states 'Promote content into permanent long-term memory' with specific verb and resource. Distinguishes from siblings by calling it 'the primary path from ephemeral to permanent memory'.

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 says to use for preserving important insights, decisions, patterns, or knowledge. Provides context but no explicit alternatives or when-not-to-use.

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 implies a read-only search operation but does not explicitly state it is non-destructive, authorization requirements, or rate limits. The description is adequate but could be more explicit about safety.

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, front-loaded with key information, and clearly 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 12 parameters and no output schema, the description explains the output format and sibling tools but does not elaborate on filtering parameters like scope or body beyond the schema.

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 100%, so baseline is 3. The description does not add meaningful details to individual parameters beyond what the 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 it performs semantic recall from long-term memory using embeddings, returns preview snippets, and explicitly distinguishes itself from sibling tools get_summary and get_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?

Provides explicit guidance on when to use this tool versus alternatives: 'use get_summary for a longer excerpt or get_full for complete chunk text.'

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 specifies that the tool reloads a cache, implying a mutation. It does not detail side effects, such as whether the operation is destructive or what happens to in-flight operations. However, for a simple cache reload with no parameters, the description is adequate.

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 three sentences: the first states the action, the second gives usage guidance, and the third specifies a condition. It is front-loaded with the verb and object, and every sentence adds value without 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 simplicity (no parameters, no output schema), the description covers the essential aspects: purpose, when to use, and a prerequisite. It could mention whether the operation is idempotent or what happens if not in registry mode, but overall it is sufficiently complete 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?

The tool has zero parameters, so the input schema fully covers the interface. The description does not need to add parameter information, and baseline is 4. It provides context about the source and mode, which complements 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: to reload the source registry cache from a specific source (demo.source_registry). It distinguishes itself from sibling tools, which focus on memory and ingestion operations, by specifying its unique function of refreshing enabled sources for insert/search filtering.

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 the tool: after adding or removing entries to refresh which sources are enabled. It also provides a condition for effectiveness: only works when running in registry mode. While it does not explicitly mention when not to use it or suggest alternatives, the guidance is clear 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 must carry full behavioral burden. It states it's a semantic search but does not disclose any behavioral traits such as read-only nature, auth requirements, rate limits, or whether it modifies state. The description lacks details beyond the basic function, leaving the agent uninformed about important behavioral aspects.

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 key function. Every sentence adds value, and there is no unnecessary information. It is 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 8 parameters and no output schema, the description covers the core purpose and usage. It explains semantic matching and typical use cases. However, it lacks details on result format, sorting, or performance characteristics, which would be helpful for full context. Still, it is reasonably complete for a search 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 88%, so the baseline is 3. The description adds context for the 'query' parameter (emphasizing semantic matching) but does not significantly enhance meaning for other parameters. The 'source' parameter lacks any description in the schema or description text, slightly reducing clarity.

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 it's a semantic search tool for short-term memories using Jina embeddings, distinguishing it from keyword search and sibling tools like list_memories. It specifies the resource (demo.memories) and the action (semantic search by meaning), making the purpose unambiguous.

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 recall past decisions, find related context, or check if something was already discussed. While it doesn't explicitly mention when not to use or alternatives, the usage hints are sufficient for an AI agent to decide.

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 is the sole source of behavioral info. It describes actions (loading, health snapshot, heartbeat) but does not disclose side effects, idempotency, auth needs, or what happens if called multiple times. Adequate but not fully transparent.

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 well-structured sentences, front-loaded with action verbs. Every sentence provides essential information without redundancy. Highly concise and efficient.

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 (13 parameters, no output schema), the description explains what the tool does but omits what it returns. There is no mention of output format or behavior, which is a gap for an initialization tool. Adequate but not 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?

Schema coverage is 100%, so baseline is 3. The description does not add extra meaning beyond the schema for any parameter. For example, 'body' is described in schema as 'Recipient body name' and the description only mentions it indirectly. No added 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 it initializes a demo session, loads identity/workflow/status from memory, runs a health snapshot, and records a heartbeat. It specifies the tool is for use at the start of a new conversation, distinguishing it from siblings like session_close and health_check.

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 says 'Call this once at the start of every new conversation', providing clear when-to-use guidance. Lacks explicit when-not-to-use or alternatives, but the context of siblings implies when to use other 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 fully discloses behavioral traits: 7-day retention, automatic promotion of up to 5 soon-expiring memories with a 48h alert window, and that promote failures never fail the close. This adds significant 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 three sentences, front-loads the main purpose, then efficiently covers side effects and content guidelines. 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 complexity (6 params, no output schema), the description covers all essential aspects: what it does, when to use, side effects, and what to include. It's complete for agent decision-making.

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 83% (high), so baseline is 3. The description adds value by explaining the summary's content (accomplishments, pending items, context) and the promotion side effect, though parameter meanings are mostly covered by 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 saves a session close summary before ending a conversation, specifying the verb 'Save' and the resource 'session close summary'. It also distinguishes itself from siblings like session_boot by mentioning its role in context continuity and memory promotion.

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 says to use this tool 'before ending a conversation' and guides what to include in the summary. While it doesn't state when not to use it or list alternatives, the context is clear from the sibling names and description.

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 key behaviors: marked memories become invisible to search/list, remain in database for audit. It does not cover auth requirements, rate limits, reversibility, or return values, but the core side effects are explained.

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 primary action and key behavioral outcomes, followed by usage guidance. Every sentence adds value with no 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?

For a tool with 3 parameters and no output schema, the description adequately covers purpose, behavior, and usage. However, it does not mention the return value or error handling, which would be helpful for an agent to fully understand the tool's 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?

Schema description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond what the schema already provides for each parameter (ids, reason, forgotten_at). It only implicitly references them through the action 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 action ('Expire short-term memories early without permanently deleting them') and the affected resource (short-term memories in demo.memories). It explicitly differentiates from permanent deletion, setting it apart from sibling tools like 'demote_memory' or 'batch_promote'.

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 use case: 'Use this to clean up irrelevant or incorrect short-term memories before their natural expiration.' It implies when to use (cleaning) but does not mention when not to use or alternatives, though it's clear this is not for permanent deletion.

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