Server Quality Checklist

Tool Scores

• fetch_feedA
  3.6/5.0
  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. It discloses the return shape, the fact that feeds can be huge and limit caps entries, and that only publicly-accessible URLs are supported. It doesn't discuss error behavior for invalid/non-feed URLs, timeouts, or whether entries are sorted/paginated, which would make it stronger.

  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?

  Three sentences, front-loaded with the main action, followed by return fields, limit guidance, and URL scope. Every sentence earns its place and there is no repetition of schema details 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 tool with no output schema, the description explains both returned sections (metadata and entries) and gives practical limit guidance, so an agent can call it correctly. It lacks explicit failure-mode handling and sibling differentiation, but for a simple fetch-and-parse tool it is close to complete.

  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 schema already documents the url format and limit's default/meaning. The description adds only the rationale that feeds can be huge, which is useful but doesn't significantly expand on the schema. This keeps it at the baseline for schema-covered parameters.

  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 the tool fetches and parses RSS/Atom feeds and enumerates the returned metadata and entry fields, so an agent knows exactly what it does. It doesn't explicitly contrast itself with the sibling tools search_entries and list_feed_metadata, though the full-feed return implies the distinction.

  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 when to use it: when you want entries plus metadata from a public feed, and it gives practical limit guidance. However, it doesn't name alternatives or state when not to use it, such as when only metadata is needed (list_feed_metadata) or when a search over fields is required (search_entries).

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

• search_entriesA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It discloses the core read-and-filter behavior and the case-insensitive matching, but lacks additional behavioral details such as whether the entire feed is fetched and filtered locally, pagination behavior, or potential 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.

  Conciseness4/5

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

  The description is concise, with two focused sentences: the first states the primary function and the second gives a practical use case. There is no fluff, though the opening 'Fetch a feed' could be slightly more specific about returning entries.

  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 three simple parameters, no output schema, and no annotations, the description provides a solid but not fully complete picture. It explains when to use the tool and the core behavior, but does not describe return value structure or pagination, and it does not explicitly position this tool relative to fetch_feed.

  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 100%, so the parameters are already well documented in the input schema. The description does not add significant parameter-level detail beyond the schema; it mainly reinforces the filtering concept already covered by the 'query' description.

  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 states a specific action (fetch a feed and return filtered entries) and clearly identifies the matching behavior (title or summary contains a keyword, case-insensitive). It implicitly differentiates from siblings by focusing on filtered search rather than full feed fetching or metadata, but does not explicitly name the siblings.

  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 second sentence provides clear context for when to use this tool: checking a feed for specific topics without needing to process everything. It does not explicitly state when not to use it or mention alternatives like fetch_feed, so it misses the full when/when-not guidance.

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

• list_feed_metadataA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral burden and does well: it discloses that the operation fetches metadata only, does not load all entries, and indicates the returned fields. It does not explicitly claim read-only behavior, but 'Fetch metadata' clearly implies a non-mutating operation.

  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, focused sentence that front-loads the core action and purpose, then adds useful specifics. No filler or redundant phrasing is present.

  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 one-parameter tool with no output schema, the description provides sufficient context: what the tool does, what it returns, and a representative use case. It does not cover error behavior or URL validity, but those are not critical for selecting and invoking this tool correctly.

  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 adds a small semantic detail ('one or more feeds') that is not enforced by the schema, but it does not significantly deepen understanding of the urls parameter beyond what the schema already says.

  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 states a specific verb ('Fetch metadata') and resource ('feeds'), and clearly distinguishes from loading all entries. It also lists the exact metadata fields returned, making the tool's purpose unambiguous and distinct from siblings like fetch_feed.

  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 clear context for use: building a dashboard of followed feeds and explicitly notes this tool avoids loading all entries. It implies the alternative is fetching full feed content, though it does not name siblings 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.