server-memory

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

No annotations provided; description compensates by disclosing deduplication, semantic similarity matching, protected obs_types, and importance affecting compression. Missing failure 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?

Well-structured with bullet points listing parameters and behaviors. Slightly verbose but each 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?

Output schema exists, so return values not needed. Description covers dedup, compression, and obs_types. Lacks entity existence handling or error scenarios.

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 has 0% description coverage and a vague 'additionalProperties: true' array. Description adds critical detail: expected fields (entityName, contents, optional source, confidence, tags, importance, obs_type) and their 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?

Clear verb+resource: 'Add observations to existing entities.' Distinguishes from sibling tools like create_entities which create new entities.

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 when-to-use or alternatives among siblings (e.g., delete_observations). Usage is implied but not guided.

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?

Describes the default backup location and parameter override, but does not disclose potential effects (e.g., whether it overwrites, locks database, or success/failure behavior). Without annotations, more detail would be beneficial.

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, front-loaded with the purpose, no unnecessary words. Efficient and clear.

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 tool with one optional parameter, the description covers essential behavior and parameter usage. Output schema exists but its absence in the description is acceptable.

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 coverage, the description adds meaning to the only parameter (dest_path) by explaining its purpose ('override the backup location') and providing the default path. Lacks format constraints but suffices.

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 ('Create a backup') and the resource ('the memory database'). It distinguishes itself from sibling tools by being the only backup operation.

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 on when to use this tool versus alternatives, or when not to use it. Since backup is unique, it's less critical, but still no explicit 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 must carry the burden. It discloses one behavioral trait: skipping duplicates by name. However, it does not mention permissions, error handling, or what happens on duplicate (overwrite vs. skip). More context on side effects is needed.

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 concise sentences with no fluff. The first sentence states the purpose, the second details parameters, and the third provides a key behavior. Information is front-loaded 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 presence of an output schema, the description does not need to detail return values. It covers the essentials: what is needed, what is optional, and duplication behavior. It could mention the return format or success/failure signals, but the output schema likely handles that. The description is adequate for a creation 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 0% description coverage, leaving the agent with only property names. The description compensates by listing required (name, entityType) and optional fields (observations, tags, metadata) with their types. This adds significant meaning beyond the bare schema, though the nested structure is not fully detailed.

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 creates new entities in the knowledge graph and specifies the required and optional fields. However, it does not explicitly differentiate from sibling tools like 'create_relations' or 'add_observations', which limits its ability to help an agent choose among them.

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 creating entities with specific fields, but it provides no guidance on when to use this tool versus alternatives (e.g., when to use 'create_entities' vs. 'add_observations' separately). It lacks explicit when-to-use or when-not-to-use instructions.

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 adds moderate value by detailing required fields and constraints, but lacks details on side effects, failure modes, or idempotency.

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 (3 sentences), front-loaded with the purpose, and every sentence adds distinct value: action, field details, constraints.

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 an output schema exists, the description covers purpose, parameter structure, and key constraints. It omits behavioral details like idempotency, but is largely complete for a simple creation 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 0% and the schema uses additionalProperties: true, making it vague. The description fully compensates by listing all required and optional fields with types, providing essential meaning.

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 creates relations between entities, using the verb 'create' and resource 'relations'. It distinguishes from sibling tools like create_entities and delete_relations.

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 specifies a prerequisite ('Both entities must exist') and a style guideline ('Use active voice for relationType'), but does not provide explicit when-to-use or 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?

With no annotations, the description carries the full burden. It discloses soft delete default, cascading, and hard delete option, but lacks details on reversibility, required permissions, or side effects beyond cascading. Some transparency 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?

The description is two sentences, front-loaded with the main action, and contains no redundant words. Every word 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?

Given the absence of annotations and the complexity of a delete tool with cascading, the description lacks details on error cases, return values (despite output schema existence), and specific side effects on related data. It feels incomplete for safe 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 schema has 0% description coverage. The description clarifies the 'hard' parameter's function (soft default, hard permanent) but does not add meaning to 'entityNames' beyond the parameter name, leaving ambiguity about format or constraints. 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 'Delete entities' with a specific verb and resource, and adds detail about soft delete default and cascading to relations, distinguishing it from sibling tools like create_entities and merge_entities.

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 guidance on using the 'hard' parameter for permanent deletion, but does not explicitly state when to use this tool over others or when not to use it, nor does it mention prerequisites or consequences of cascading.

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 does not disclose behavioral traits such as reversibility, side effects, or authorization requirements. Only states the delete action without further context.

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 efficient sentences: first states purpose, second explains parameter format. 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?

Covers parameter structure but omits output format, error handling, and behavior when observations don't exist. Sufficient for basic use but incomplete for a delete operation without 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?

Schema has 0% description coverage for the 'deletions' parameter; the description adds critical structure details (entityName and observations list), compensating for schema opacity.

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 the action 'delete' and resource 'observations from entities', distinguishing it from siblings like delete_entities and delete_relations.

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 necessary parameter structure (entityName, observations list) but lacks explicit guidance on when to use vs alternatives or prerequisites.

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 lacks disclosure of behavioral traits such as permanence, cascading effects, or error handling. It only states the action and parameter format, which is insufficient 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 very concise, consisting of two sentences that first state the purpose and then explain the parameter format. No unnecessary 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?

The description is fairly complete for the parameter structure but lacks context about behavioral aspects like error states or idempotency. The presence of an output schema reduces the need to explain return values, but behavioral transparency is missing.

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 provides an open array of objects with no property definitions. The description adds the required structure (from, to, relationType), compensating for the 0% schema coverage. However, it does not specify whether these are required or optional.

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 (delete) and resource (relations from the knowledge graph). However, it does not differentiate from sibling tools like create_relations or delete_entities, which could be clarified.

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. There is no mention of prerequisites, edge cases, or conditions for 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 carries full burden. States it exports data, but fails to disclose if it is read-only, any side effects, or performance implications.

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 no wasted words. Front-loaded with the core action, then provides format detail.

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?

Output schema exists, so return values are partially covered. However, the description omits details on what the export returns (e.g., file, stream, data structure) and any size/performance considerations.

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 has 0% description coverage for the 'format' parameter, but the description explains valid values ('json' or 'jsonl') and their compatibility, adding necessary context.

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 'Export the full knowledge graph,' specifying verb and resource. Distinguishes from sibling 'import_graph' and 'read_graph' by implying full export, but could be more specific about the action.

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?

Mentions compatibility with old server-memory, but does not explicitly state when to use this vs. siblings like 'read_graph' or when not to use it.

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 reveals full behavior: shows current content, version number, importance, obs_type, and all previous versions with timestamps. No mention of auth or limits though.

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 that front-load the purpose and add necessary detail 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 output schema existence, description is complete enough for a history retrieval tool, though could mention result ordering or pagination.

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 0%, but description adds meaning by explaining entity_name context and the filtering use of content_prefix beyond schema definitions.

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 'Get observation version history for an entity' and details what information is returned, distinguishing it from sibling tools that add, delete, or manage observations.

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 guidance on using 'content_prefix' to filter observations, but lacks explicit when-not-to-use or alternative tool recommendations.

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 auto-format detection, compatibility, and skip behaviors (duplicates, missing entities). However, it does not mention whether the import is destructive (overwrites), what happens on error, or return value details (output schema exists but not described).

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 very concise, with two short paragraphs. All sentences add value: main purpose first, then compatibility and behaviors. 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 (import with auto-format detection, skip logic) and the lack of annotations or parameter descriptions, the description covers key behaviors but misses details like expected data structure, success/error handling, and performance implications. Output schema exists, so return value documentation is not required, but more context would be helpful.

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 adds some meaning by stating the data parameter expects JSON or JSONL format. But it does not specify the expected structure (e.g., entities and relations array) or provide examples, leaving 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 it imports knowledge graph data and specifies auto-detection of JSON/JSONL formats. It also mentions compatibility and skip behaviors. However, it does not explicitly differentiate from sibling tools like create_entities, which also creates entities but individually.

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 context about compatibility with old server-memory files and mentions skip behaviors, implying usage. But it lacks explicit when-to-use/when-not-to-use guidance and does not name alternatives like create_entities for bulk vs individual imports.

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 the full burden. It discloses the side effect of auto-creating missing entities, which is a key behavioral trait. However, it does not mention other important aspects like idempotency, overwrite behavior, or required permissions.

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 (three short sentences) and front-loaded with the core purpose. Every sentence adds unique value: the first states the primary function, the second reveals a side effect, and the third provides actionable examples.

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 5 parameters and no annotations, the description is somewhat incomplete. It does not explain the role of most parameters or how they interact. The existence of an output schema mitigates the need to describe return values, but the description lacks depth for proper 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?

Schema description coverage is 0%, and the description only adds context for the 'action' parameter by listing common values. The other four parameters (summary, entity_names, tags, metadata) receive no elaboration, leaving their semantics unclear despite the schema titles.

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-resource combination: 'Record what happened this turn.' It also lists common actions, which distinguishes it from sibling tools that focus on entity manipulation or memory queries.

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 list of common actions, but does not explicitly state when to use this tool versus alternatives like add_observations or create_entities. No guidance on when not to use it is provided.

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 the burden. It discloses that delete cannot remove system tags and cleanup removes expired ephemeral items, but does not mention other side effects, permissions, or state changes beyond what is obvious.

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 uses a bullet-like list for actions. It front-loads the purpose and action summary, though some sentences could be more terse.

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 7 parameters and an output schema, the description covers action semantics but lacks details on default behavior, accepted values for color, and response structure. It is adequate but not 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 description adds meaning to parameters: name is required for create, entity_name and tag_name for tag/untag, and optional fields for create. This compensates for the 0% schema description 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 manages tags and lists specific actions (list, create, delete, tag, untag, cleanup), each with a brief explanation. This distinguishes it from sibling tools focused on entities, relations, or observations.

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 listing actions but does not explicitly state when to use this tool over alternatives or provide exclusions. It lacks guidance on prerequisites or context for each action.

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?

Describes returns and token size, but with no annotations, lacks full disclosure on side effects, determinism, or limitations beyond the brief overview.

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?

Efficiently organized, front-loaded with definition, then returns, usage, parameters. No unnecessary 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?

Covers key aspects for a read tool with optional params and an output schema, though could address error cases or output format more.

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?

Despite 0% schema coverage, the description fully explains each parameter's purpose and usage, adding significant meaning 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 it is a lightweight context snapshot for durable recall, listing returns. It is specific but could more explicitly differentiate from siblings like memory_context_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 tells when to call (prior sessions, cross-session continuity) and when to skip (one-off answers), plus parameter usage 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?

With no annotations, the description carries the full burden. It discloses the output content (pinned entities, last 10 recent activities, recently changed entities) and the expected token cost (~500-1500 tokens). However, it does not explicitly state whether the operation is read-only or has side effects, which would improve 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 extremely concise: three sentences with no fluff. The most important information (purpose and when to use) is front-loaded. 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?

Given that an output schema exists, return values are covered. However, the description lacks parameter explanations, which are essential for correct usage. The tool's purpose and usage context are well covered, but the missing parameter semantics reduces completeness significantly.

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, meaning descriptions are entirely absent from the schema. The tool description fails to explain the 'project' and 'budget' parameters, leaving the agent without guidance on how they affect the output (e.g., does 'budget' control the token limit?). This is a critical 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 explicitly states it returns a rich context snapshot with pinned entities, full observations, recent activity, and recently changed entities. It distinguishes itself from 'memory_context' by specifying a different use case (deep bootstrap vs ordinary scoped recall). The verb 'returns' clarifies the action.

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 guidance: 'Use only when compact recall is insufficient for a cross-session task' and 'Prefer memory_context for ordinary scoped recall.' This explicitly tells when to use this tool and when to use an alternative.

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 lists the specific statistics returned, providing good transparency about the output, though it does not mention any potential costs or side effects (which may be minimal for a stat retrieval).

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 concise sentence with the main action front-loaded, followed by a clear list of statistics, containing no extraneous 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 output schema exists (not shown) and no parameters, the description provides a complete overview of what the tool returns, making it fully understandable for 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?

No parameters exist, so the description does not need to add parameter information. Schema coverage is 100%, and the description is sufficient 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 retrieves memory statistics and enumerates specific types (entity/relation/observation counts, tag distribution, DB size, orphan entities, deleted items), distinguishing it from sibling tools like read_graph or memory_context.

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; however, the purpose is straightforward and implied for obtaining memory usage stats.

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?

The description discloses key behaviors: source is soft-deleted, strategy affects observations, relations/tags are transferred, and self-relations are removed. However, no annotations are present, and it lacks clarity on reversibility, permissions, or failure cases.

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 (four sentences) and front-loaded with the core action. Every sentence adds value without unnecessary 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 presence of an output schema, the description covers the essential behavior: merge logic, soft-delete, strategy options, and transfer of relations/tags. It is complete enough for an AI agent to understand the tool's effect, though it could mention ordering 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?

With 0% schema description coverage, the description fully explains all three parameters: source, target, and strategy (with values 'combine' and 'dedupe'). It adds meaning beyond the bare schema by specifying strategy effects and the soft-delete outcome.

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 merges a source entity into a target entity, with the source being soft-deleted. This immediately distinguishes it from sibling tools like create_entities or delete_entities, as it involves combining two entities.

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 (e.g., delete_entities + create_entities). It does not specify prerequisites or scenarios where merging is preferred over other operations.

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 present, so the description carries the full burden. It explains depth parameter behavior (exact, neighbors, BFS), but does not disclose whether the operation is read-only, any side effects, auth requirements, or data limits. The word 'open' could imply loading or fetching, but mutability isn't addressed.

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, using a few sentences to convey purpose and depth behavior. It is front-loaded with the main purpose. Every sentence is meaningful with no 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 has an output schema (not shown), the description need not detail return values. However, it does not address how this tool relates to siblings like 'search_nodes' or 'read_graph', nor typical use cases. It adequately covers the core behavior for a focused 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 0%, so the description must add meaning. It clearly explains the depth parameter with specific values. The 'names' parameter is only described as 'entities by name' without further detail on format, case sensitivity, or uniqueness. Depth gets thorough treatment; names could benefit from more precision.

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 opens specific entities by name, with detailed depth parameter behavior. It differentiates from siblings like 'search_nodes' and 'read_graph' by focusing on targeted entity opening.

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 use for opening specific entities with optional expansion, but lacks explicit guidance on when-to-use vs alternatives (e.g., search_nodes) and when-not-to-use. No prerequisites or context are provided.

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. It mentions filters but does not disclose ordering, pagination, default limits (though schema shows limit default 50), whether it is read-only, or if results are chronological. The existence of an output schema is not leveraged in description.

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, two sentences with no fluff. It front-loads the purpose and immediately provides key parameter usage details. 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?

Given 7 parameters and no annotations or output schema details, the description is insufficient. It does not explain return structure, ordering, or the limit parameter. It lacks depth for a tool with moderate 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 0%, so description must compensate. It explains time_range format and lists filter options but omits the limit parameter entirely. The descriptions for actions, entity_name, and session_id are just names with no additional 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 tool queries an activity timeline, with specific filters. It is distinct from sibling tools which focus on entities, relations, and observations. However, it could specify what kind of activity (e.g., system actions, user actions) for even greater 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 explains how to specify time range (relative or ISO) and lists filter parameters, implying usage. However, it provides no guidance on when to use this tool versus alternatives, nor are there exclusions or prerequisites 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?

With no annotations, the description must disclose behavioral traits. It mentions compression by default but does not explicitly state it is read-only, nor does it cover the behavior of limit or include_deleted parameters. Safety and side effects are not addressed.

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 very concise with two sentences that front-load the main purpose. Every sentence adds information with minimal waste, though it could be slightly expanded to cover all parameters without losing conciseness.

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 and no annotations, the description is incomplete. It explains only 3 of 5 parameters (tags, entity_types, compress) and does not mention limit or include_deleted. The presence of an output schema reduces the need to describe return values, but parameter coverage is insufficient.

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 0%, so the description must add meaning. It explains tags, entity_types, and compress, but omits limit and include_deleted. It adds value over the bare schema for three parameters, but fails to document two.

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' and the resource 'knowledge graph', specifying that it returns the graph compressed by default. While it distinguishes from write tools, it does not differentiate from other read tools like search_nodes or query_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 no guidance on when to use this tool versus alternatives. It lacks explicit context for use cases, prerequisites, or exclusions, leaving the agent to infer from the tool name alone.

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. It discloses BM25 ranking, prefix search, phrase search, boolean operators, and filter options. However, it does not mention output format, pagination, result ordering, or behavior on empty results. The 'limit' and 'compress' parameters are not described.

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 front-loaded with the core purpose. Each sentence adds value without redundancy. The list format for advanced features is efficient. No unnecessary wording.

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 presence of an output schema (handling return values) and the tool's moderate complexity, the description covers search mechanics well. Missing details about 'limit' and 'compress' parameters prevent a perfect score, but overall it provides sufficient context for an agent to use the tool 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 coverage is 0%, so description must compensate. It explains the 'query' parameter's syntax (prefix, phrases, boolean) and describes 'tags', 'entity_types', and 'time_range' with format. It omits 'limit' and 'compress', but covers most parameters with meaningful usage details 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 explicitly states 'Full-text search with BM25 ranking', clearly identifying the tool's purpose. The name 'search_nodes' reinforces the resource being searched. This distinguishes it from sibling tools like 'read_graph' (graph traversal) and 'open_nodes' (node retrieval by ID).

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 full-text search with filtering capabilities but does not explicitly state when to use this tool over alternatives. No direct comparison with siblings like 'query_timeline' or 'read_graph' is provided. The agent must infer context from the tool's name and capabilities.

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