Server Quality Checklist

Tool Scores

• save_web_conversationA
  3.8/5.0
  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 clearly states the write-to-disk action and markdown format, but does not disclose whether existing files are overwritten, whether directories are created, or any error handling. This leaves some behavioral ambiguity for a file-writing tool.

  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 sentence, front-loaded with the action verb and resource, then a practical use case. There is no filler or repetition.

  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?

  Given the tool's moderate complexity (file write with a timestamp option) and lack of annotations/output schema, the description covers the primary purpose and use case but omits edge behaviors like overwriting, file path handling, and return value. This is adequate but not fully complete.

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

  Parameters2/5

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

  Schema coverage is 67% (path and uuid are described, include_timestamps is not). The tool description adds no parameter context; it does not explain what include_timestamps does or how the parameters interact. The description does not compensate for the partially missing schema documentation.

  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 action: 'Fetch a claude.ai conversation and write it to disk as markdown.' It specifies the resource (claude.ai conversation) and output (markdown file), and distinguishes itself from siblings by emphasizing persistence to disk rather than just reading 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?

  The description gives a clear use case: 'useful for parking it in the repo (e.g. docs/context/) so it persists across sessions.' This implies when to use it, though it does not explicitly name alternatives or state 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.

• list_web_conversationsA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It states the ordering ('newest first') and return fields (uuid, title, timestamps), which is useful, but it does not explicitly state that this is a read-only operation, nor does it mention any access requirements or potential side effects. The listing nature implies safety, but it is not explicit.

  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, front-loaded with the primary purpose, followed by return type and an alternative tool pointer. Every sentence contributes value without unnecessary verbosity.

  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?

  For a simple list tool with pagination, the description covers the essential purpose, ordering, return fields, and a related alternative. Since the schema already documents parameter syntax and there is no output schema, the description's explicit mention of returned fields fills the gap. Minor omission: it does not describe pagination behavior itself, but schema handles that.

  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 (limit, offset, contains) already have clear descriptions in the schema, totaling 100% coverage. The description adds no additional parameter-specific meaning beyond what the schema provides, so a baseline score 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 lists conversations from claude.ai web account, with the specific verb 'list' and resource. It also distinguishes itself from the sibling read_web_conversation by noting it returns multiple conversations and pointing to that tool for pulling one in.

  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 an explicit alternative: 'Use read_web_conversation to pull one in,' which conveys when to use a different tool for single-conversation retrieval. However, it does not elaborate on exclusions for the other sibling tools (debug_connection, save_web_conversation), though their purposes are inferable from their names.

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

• read_web_conversationA
  4/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It states 'fetch' (a read verb) and 'as markdown' which discloses return format. However, it does not explicitly disclose that this is read-only, nor does it mention truncation behavior or any potential side effects, though the schema covers max_chars. It's adequate but not rich.

  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?

  One sentence, 20 words, front-loaded with verb and resource. No fluff.

  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?

  For a simple read tool with three params and no output schema, the description plus schema cover the core need: what it does, output format, and use case. However, it doesn't mention error conditions, authentication, or relationship to debug_connection, but these are not critical for successful invocation.

  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 description coverage is 67% (uuid and max_chars described). Description adds no parameter-specific info, but the schema's uuid description links to list_web_conversations, and max_chars explains truncation. The include_timestamps parameter lacks description in both schema and tool description, leaving a gap.

  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 specific verb 'fetch' and resource 'full transcript of one claude.ai conversation', with output format 'markdown'. It clearly distinguishes from siblings like list_web_conversations (which lists conversations) and save_web_conversation (which likely saves/shares).

  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?

  Provides clear context: 'so it can be used as context in this Claude Code session' indicates when to use. However, it does not explicitly mention alternatives or when not to use, though the sibling list tool is implied through the schema's uuid reference.

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

• debug_connectionA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. The verbs 'check' and 'inspect' suggest read-only diagnostics, but the 'raw API path' option could be interpreted as an arbitrary request without explicitly noting that it is non-mutating. This leaves some ambiguity about whether any side effects could occur.

  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 only two sentences, begins with the primary purpose, and then appends the optional behavior. Every sentence serves a clear function, and there is no redundant wording or unnecessary detail.

  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 single optional parameter, no output schema, and no annotations, the description covers the main behavior and the optional parameter's use case well. It implies the expected outputs (whether the key works, the resolved org id, and the raw response shape) without explicit formatting, which is acceptable for a debugging tool of this simplicity.

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

  Parameters4/5

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

  The input schema already covers raw_path with 100% description coverage, so the baseline is 3. The description adds meaning by explaining the purpose of the parameter: 'to inspect its shape when an endpoint changes,' which goes beyond the schema's simple example and helps the agent understand when to populate it.

  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 opens with 'Check whether the session key works and which org id is resolved,' which is a specific verb and resource. This clearly distinguishes it from the sibling conversation tools, which focus on managing conversations rather than debugging the underlying connection.

  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 implies when to use the tool: when you need to verify the session key or resolved org id, and optionally to inspect raw API responses when an endpoint changes. However, it does not explicitly name alternatives or state when not to use it, so it lacks the full exclusion guidance needed for a 5.

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