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

With no annotations, the description bears full burden. It reveals the three synced stores (SQLite, Chroma, Markdown), indicating persistence. However, it does not mention irreversibility, confirmation requirements, or error states.

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 sentence with a parenthetical detail, front-loaded with the purpose. Slightly concise but 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?

Given one parameter and no output schema, the description provides basic purpose and sync info but lacks return format, error behavior, and parameter details.

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

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

Schema coverage is 0%. The description adds no meaning beyond the schema: it does not explain what the 'id' parameter refers to or its format.

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 (删除, delete) and resource (记忆, memory) and specifies three synced stores. It distinguishes itself from siblings like remember and update_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 explicitly says to call when the user wants to delete/forget a memory. It lacks explicit when-not-to-use or alternatives, but the context is clear.

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 return content (complete with links). No annotations provided, but readability is high; could explicitly state read-only nature.

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, front-loaded with action, 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?

Fully describes a simple retrieval tool. Covers purpose, usage, and output (content with links).

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?

Only parameter 'id' is explained in description as a required memory identifier. Compensates for 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?

Clearly states tool retrieves a single memory by ID, including associated links. Distinguishes from siblings like search_memories and list_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 to call when a specific ID is known, indicating usage context. Could benefit from mentioning 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, so description carries full burden. It discloses sorting order and exclusion of content, but lacks details on pagination, limits, or authentication needs.

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

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

Two short sentences, front-loaded with purpose. Every word earns its place, no 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?

For a simple list tool with one optional parameter and an output schema, the description is nearly complete. Could mention pagination, but output schema may cover return structure.

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%. Description mentions category filter, but adds no value beyond the parameter name 'category'. Does not explain valid values or format.

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 lists memories with optional category filtering, sorted by update time descending, and excludes content. It distinguishes from siblings by explicitly noting the sorting and filtering behavior.

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 'call when browsing/overviewing existing memories', providing clear context. Does not mention when not to use or alternatives, but siblings imply search_memories for searching.

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. It discloses that it returns memories with links if content contains [[link]] syntax, but does not detail fusion algorithm, auth requirements, or rate limits. 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 plus a third about links; no wasted words. Could be improved by structuring as bullet points for scanning, but overall 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 that output schema exists (covering return values) and there are no annotations, the description covers purpose, usage, and link behavior. However, it omits details about the fusion method and does not explain all parameters, leaving moderate gaps.

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

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

Schema coverage is 0%, and the description does not explain individual parameters (query, top_k, category) beyond implying query as the user's question. top_k and category are left to the schema defaults. Insufficient compensation for the lack of schema descriptions.

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 retrieval tool using semantic+keyword+title fusion, returning memories with links. The verb '检索' (retrieve) and resource '记忆' (memories) are specific, but it does not explicitly distinguish from sibling 'search_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 tells when to call (user asking about past records, historical decisions, pitfalls) via example phrases. Lacks when-not-to-use or alternative tool references, but the context is clearly conveyed.

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 multi-sync storage, auto-embedding, and the ability to reference other memories. It does not mention return values or error handling, but for a create operation, the disclosed behavior 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 concise at three sentences, each sentence adds value: first sentence states core function, second gives usage trigger, third explains advanced features (references, category, scope). No redundant 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 5 parameters, no output schema, and no annotations, the description covers purpose, usage, and parameter semantics adequately. It does not describe return values or success/failure, but for a simple storage tool, the information provided is sufficient for an AI agent to use it correctly.

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, so the description must compensate. It explains the category values (user/project/process/agent) and scope values (user/project/session), and notes that content can reference other memories. It does not detail title or tags beyond their names, but adds significant value overall.

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 states the tool stores a persistent memory (verb+resource) with specific storage backends and auto-embedding. It distinguishes from siblings like recall and forget by providing usage triggers (when user says 'remember/note/save'). The purpose is specific and clear.

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 call the tool (when user says certain phrases). It implies context for use but does not explicitly exclude scenarios or mention alternatives like update_memory. However, the sibling list provides differentiation, and the trigger phrases are helpful guidelines.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the tool filters only metadata ('不含正文'), which is a critical behavioral trait. However, it does not mention read-only nature, pagination, sorting, or required permissions, leaving gaps in transparency for a safe invocation.

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 short sentences with no redundancy. It front-loads the key filtering dimensions and the exclusion of body content, then provides a usage directive. Every word earns its place.

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 (which likely documents return values), the description adequately covers the filtering scope and behavioral note (no body). It lacks details on combining filters, pagination, or default limit behavior, but the schema and output schema partially fill these gaps. Overall, sufficient for a focused filter 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 description references three of four parameters (category, tag, agent) by their filtering roles, adding meaning beyond the bare property names in the schema. However, the 'limit' parameter is not mentioned, and with 0% schema description coverage, the description does not fully compensate by explaining parameter types, constraints, or how to combine filters.

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 filters memories by category, tag, and source agent, and explicitly notes it excludes body content. The phrase '需精确筛选时调用' (call when precise filtering is needed) differentiates it from semantic or list operations, making the purpose very specific and distinguishable from siblings like 'recall' or 'list_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?

The description explicitly says '需精确筛选时调用', guiding the agent to use this tool when precise structural filtering is required. It implies not for fuzzy or semantic search, though it does not explicitly name alternatives or state when not to use it. The context is clear enough for an agent to choose appropriately among siblings.

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

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

Given no annotations, the description carries full burden. It discloses that changing content triggers vector recalculation and Markdown refresh, which is a key behavioral trait beyond a simple update. It could mention other aspects like idempotency or auth needs, but the disclosed behavior adds value.

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 short sentences, front-loaded with the action and key behavior, followed by usage guidance. No wasted words; every sentence earns its place.

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 adequate for a simple update tool. It covers purpose, usage, and a key behavioral effect. However, it does not mention return values (no output schema) and omits that 'id' is required, but these gaps are minor given the tool's simplicity.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning to the 'content' parameter by noting it triggers recalculation, but does not explain other parameters (id, tags, scope, title, category). This is partial compensation, leading to a score of 3 (baseline 4 with no param info is not fully met).

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 'Update existing memory' and specifies that changing content recalculates vectors and refreshes Markdown. It distinguishes from siblings like 'remember' (create) and 'get_memory' (read) by stating 'call when modifying/supplementing existing 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 explicitly says 'call when modifying/supplementing existing memory', which provides clear context for when to use this tool. It does not explicitly mention when not to use it, but the sibling context implies differentiation from creation or retrieval tools.

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

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

No annotations provided, so description carries full burden. It clearly indicates a read-only information retrieval, but could explicitly state it does not modify state. Given the obvious safe nature, score is high.

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 output, second gives usage instruction. No wasted words, front-loaded with purpose.

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

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

Lists returned items satisfactorily for a simple info tool. No output schema, but description covers key contents. Could add more on output format but 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?

No parameters, baseline score of 4. Description correctly implies no input needed, and schema coverage is 100%.

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 returns specific information: Agent identity, project root, data directory, and memory counts by category. It uses a specific verb '返回' (returns) and resource, distinguishing it from sibling tools like 'get_memory' or 'remember'.

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?

Explicit guidance provided: '会话开始时先调用' (call at the start of a session). This tells the agent precisely when to use this tool, though it does not mention alternatives—but the sibling tools are different in purpose.

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