Server Quality Checklist

Tool Scores

• list_topicsA
  3.7/5.0
  Behavior4/5

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

  With no annotations, the description discloses meaningful behaviors: it is a 'lofi version' returning a specific lightweight set of fields, it uses a '(!)' prefix convention for important topics, and it returns a 'rate_limited' payload with retry_after_seconds and retry_at_utc instead of erroring on rate limits. It could mention pagination or ordering, but the provided detail is useful.

  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 compact and front-loaded: the core listing action and output fields appear first, followed by the rate-limit exception. The phrase 'lofi version' is slightly ambiguous but does not distract from the main purpose.

  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 a simple one-parameter tool, the description covers the core semantic (list topics), the return fields, and the only exceptional behavior (rate limiting). It does not mention pagination or ordering, but nothing in the provided schema or complexity suggests those are required for correct basic invocations.

  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 sole parameter forum_id is 100% covered by its schema description ('4PDA forum ID.'). The description adds some context by specifying the tool lists topics within that forum, but that is already implied, so there is no significant extra semantic value beyond the schema.

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

  Purpose4/5

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

  The description clearly states a specific verb ('List'), resource ('topics in a 4PDA forum'), and the returned fields (id, title, reply count, is_important). It does not explicitly name siblings list_forums or list_posts, but the distinction is evident from the resource term itself.

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

  Usage Guidelines3/5

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

  The description implies this is the tool for listing topics for a given forum_id, and gives conditional guidance for rate-limit handling ('wait that long before calling again'). However, it does not explicitly state when to choose this over sister tools like list_forums or list_posts.

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

• list_forumsA
  4.4/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden for behavioral disclosure. It goes beyond a simple 'list' by explaining the rate-limit behavior: a 'rate_limited' payload with retry_after_seconds and retry_at_utc is returned instead of an error, telling the agent exactly what to expect and how long to wait.

  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 efficient and front-loaded. The first paragraph states the core behavior, including the optional parameter's impact, and the second paragraph adds the rate-limit detail. No unnecessary words or filler.

  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 one optional parameter and no output schema, the description explains what the function returns, how the parameter changes behavior, and how rate limiting is handled. It avoids describing response field names, which could be considered a minor gap without an output schema, but nothing essential is missing for correct invocation.

  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?

  Schema coverage is 100%, so the parameter is already documented in the input schema. However, the description adds meaning by clarifying that omitting forum_id returns top-level categories (the forum tree roots) and that IDs are 4PDA forum IDs. This is useful context beyond the schema's terse 'Forum ID. Omit to list top-level categories.'

  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 4PDA forum categories/subforums, a specific verb and resource, and explains the two modes (with and without forum_id). This separates it from the sibling tools list_topics and list_posts, which deal with topics and posts rather than forum structure.

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

  Usage Guidelines3/5

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

  The description explains what the tool returns in both modes but does not explicitly name alternatives or say when not to use it. The mention of 'a summary of its topics' implies list_topics might be used for full topic listings, but that guidance is left to inference rather than stated explicitly.

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

• list_postsA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden, and it does well. It discloses rate-limit behavior with retry fields, internal link rewriting, and the pinned-header behavior across pages. These are meaningful behavioral traits beyond the schema.

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

  Conciseness5/5

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

  The description is well-structured: it front-loads the core purpose, then adds pagination details, and ends with a separate rate-limit notice. Every sentence contributes distinct information without unnecessary filler.

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

  Completeness5/5

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

  For a simple paginated read tool, the description covers output content, pagination semantics, page size, and exceptional rate-limit response. No output schema exists, but the description sufficiently describes what the caller receives and how to handle retries.

  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?

  Schema coverage is 100%, so the schema already documents both parameters. The description adds extra interpretative value: pages are 1-indexed, each page has 20 posts, and rate-limit retry behaviors are tied to calling again. This goes beyond basic type hints.

  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 a specific verb and resource: 'List posts on a page of a 4PDA topic (lofi version)', and it specifies the returned content: author, date, and HTML body. This makes it clearly distinct from the sibling tools list_forums and list_topics.

  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 clear operational context: pages are 1-indexed, each page has 20 posts, and the pinned header is dropped on later pages. It doesn't explicitly say 'use list_topics instead' or 'don't use for forums', but the scope is concrete enough that an agent can decide when to invoke it.

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