Server Quality Checklist

Tool Scores

• forget_fileA
  3.8/5.0
  Behavior3/5

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

  Without annotations, the description carries the burden of disclosing behavior. It states that it '删除所有记忆' (deletes all memories) for the file, which conveys destructiveness and scope. However, it doesn't mention irreversibility, permissions, or side effects on other components (e.g., embeddings), leaving some behavioral gaps.

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

  Conciseness4/5

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

  The description is a single, front-loaded sentence stating the core action, followed by a list of trigger phrases that aid usage. It is efficient, though the trigger list is somewhat lengthy.

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

  Completeness3/5

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

  The tool is simple (one parameter, no output schema), but without annotations, the description should cover more context. It confirms the destructive action and usage triggers, but doesn't mention error cases, irreversibility, or interaction with sibling tools, making it adequate but not comprehensive.

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

  Parameters3/5

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

  Schema coverage is 100%, and the file_path parameter already has a clear description ('要删除记忆的文件的完整路径'). The tool description adds little beyond '指定文件', so it doesn't provide additional semantic value beyond the schema.

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

  Purpose5/5

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

  The description uses a specific verb '删除' (delete) and resource '指定文件的所有记忆' (all memories of the specified file), clearly stating the tool's function. It distinguishes from sibling tools (embed_file, search_memory, list_memories) by targeting removal of memories rather than creation, search, or listing.

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

  Usage Guidelines4/5

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

  It provides explicit trigger phrases ('忘记这个文件', '删除记忆', etc.) indicating when to use the tool. It doesn't explicitly contrast with alternative tools but offers concrete user-intent examples, giving clear usage context.

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

• search_memoryA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full responsibility. It states the tool 'searches' content but does not explicitly disclose that it is read-only, whether it modifies memories, or how results are returned. Though the action implies non-destructive behavior, that is not stated, and the description lacks details about pagination, ranking, or output format.

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

  Conciseness4/5

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

  The description is front-loaded with a clear purpose sentence, then expands with use cases and trigger words. While the trigger word list is somewhat verbose, it serves practical guidance for deciding when to invoke the tool. Overall, it is efficient and not overly redundant.

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

  Completeness3/5

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

  With no output schema, the description should cover return behavior, but it does not mention what the tool returns or how results are presented. The usage context is well covered, but the lack of return format and any limitations (e.g., max limit) leaves gaps for an agent invoking the tool.

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

  Parameters3/5

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

  Schema coverage is 100%, so the baseline is 3. The description does not add any parameter-specific information beyond the schema, but since the schema already documents each parameter fully (query, limit, source, file_type), this is adequate.

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

  Purpose5/5

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

  The description explicitly states the tool searches a learned knowledge base, which is a specific verb+resource pairing. It distinguishes itself from siblings like embed_file (add content), list_memories (list memories), and forget_file (delete) by focusing on retrieval.

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

  Usage Guidelines4/5

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

  The description provides a clear when-to-use list covering many scenarios (finding previous content, historical info, saved files, discussions, code, documents) and even gives trigger words. However, it does not explicitly mention when not to use it or name alternative tools, which would fully meet the 'explicit when/when-not/alternatives' criterion.

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

• embed_fileA
  3.9/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the full burden of behavioral disclosure. It mentions DeepSeek automatic preprocessing as a notable behavior, but does not explain side effects such as duplicate handling, overwriting existing entries, permissions required, or what the tool returns. Some transparency is offered, but key behavioral details are missing.

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

  Conciseness5/5

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

  The description is a single well-structured paragraph that leads with the core use case, then lists concrete trigger phrases, and closes with one relevant feature. There is no filler or redundant content—every sentence earns its place.

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

  Completeness3/5

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

  For a write tool with no output schema and no annotations, the description explains when to use it and what it does, but omits important context such as return values, error behavior, and what happens if a file is already embedded. It is adequate for basic understanding but has clear gaps for an agent expecting robust guidance.

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

  Parameters3/5

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

  All three parameters are fully described in the schema (100% coverage), including file_path, description, and the preprocess boolean with default. The description adds no additional parameter-specific meaning beyond the schema, so the baseline of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool's function: saving file content, learning new knowledge, remembering files, adding to knowledge base, and storing code/documents. It lists explicit trigger phrases ('学习这个文件', '记住这个文件', '保存到记忆', etc.), which unambiguously differentiates it from sibling tools (search_memory, list_memories, forget_file) by focusing on adding content to memory.

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

  Usage Guidelines4/5

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

  The description provides explicit trigger scenarios and user expressions that indicate when to call this tool, making the usage context very clear. However, it does not explicitly state when not to use it or mention alternative tools like search_memory for retrieval, so it lacks exclusions but still offers strong guidance.

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

• list_memoriesA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses the primary action (listing files) but does not elaborate on what 'statistics' means or whether the operation has side effects. The read-only nature is implied but not explicitly stated.

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

  Conciseness5/5

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

  The description is two sentences: the first states the function, the second provides example trigger phrases. Both sentences are informative and necessary, with no wasted words.

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

  Completeness4/5

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

  Given the tool's low complexity (one optional parameter, no output schema), the description adequately covers the main function and typical use cases. However, the vague term 'statistics' could be more specific, and the output format is not described.

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

  Parameters3/5

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

  The schema already fully documents the optional file_type parameter with an example. The description does not add additional parameter semantics beyond what the schema provides, so the baseline score applies.

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

  Purpose5/5

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

  The description clearly states the tool lists all learned files with their statistics, using a specific verb (list) and resource (learned files). It also provides example user queries, distinguishing it from sibling tools like embed_file, search_memory, and forget_file.

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

  Usage Guidelines4/5

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

  The description provides explicit trigger phrases indicating when to use this tool, such as '查看已学习的文件' and '列出所有内容'. It does not explicitly mention alternatives or exclusions, but the clear context of user intent makes it a solid guidance.

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