Server Quality Checklist

Tool Scores

• get_best_of_the_restB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It mentions that headlines may be outbound and that it is not tax advice, which are minor traits. However, it does not disclose read-only nature, potential authentication needs, rate limits, or response format. The 'Do not fetch Hopper' instruction hints at a constraint but lacks context. This is insufficient for a tool with no annotation support.

  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, about four short sentences, and front-loads the core action (GET request). Each sentence conveys a distinct piece of information without unnecessary verbosity. However, the abrupt inclusion of 'Not tax advice' and 'Do not fetch Hopper' feels slightly disjointed and could be better integrated.

  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 no-parameter GET tool, the description covers the core action and scope, but leaves open questions: what the response looks like (no output schema), why Hopper should be avoided, and whether any authentication is needed. Its brevity is adequate but not fully complete, leaving an agent with some uncertainty about the tool's behavior.

  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 tool has zero parameters, so the schema coverage is trivially 100% and there is nothing to document. Per the baseline for 0 parameters, a score of 4 is appropriate because the description does not need to add parameter meaning beyond what the empty schema already conveys.

  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 it performs a GET on /best-of-the-rest.json from the public newspaper's curated field. It is specific about the resource and scope ('public newspaper only'), though it does not explicitly name sibling tools to distinguish itself, it conveys a distinct purpose.

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

  Usage Guidelines2/5

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

  The description provides a caution about not fetching Hopper and notes 'public newspaper only', but it does not explain when to use this tool over its siblings (e.g., get_edition, get_feed) or what conditions would lead to choosing an alternative. There is no explicit when/when-not guidance relative to the other tools.

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

• get_llms_txtB
  3.2/5.0
  Behavior2/5

  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 mentions 'Headlines may be outbound' and 'Do not fetch Hopper' as warnings, but fails to describe side effects, error behavior, or the nature of the response (e.g., text content, potential redirects). The lack of detail on these aspects leaves the agent uncertain about what to expect.

  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 composed of four short, front-loaded sentences. The primary purpose is stated first, followed by three concise warnings that each add value. There is no redundancy or fluff, and the structure makes it easy for an agent to quickly grasp the tool's function.

  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 simple parameterless GET, the description provides the resource and some constraints, but it does not describe the output format (e.g., plain text, JSON) or likely errors. Since there is no output schema, the description should compensate by clarifying what the agent will receive, but it omits this. It is adequate for a minimal call but leaves some ambiguity.

  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 tool has zero parameters, so the description has nothing to add beyond the empty schema. The schema coverage is 100% (it is empty), and the baseline for 0 parameters is 4. The description is consistent with this and does not need to explain any 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 action ('GET /llms.txt') and the resource (the public newspaper), with an explicit purpose ('how to cite the paper'). It distinguishes itself from siblings by being the only tool fetching llms.txt, although it does not name the siblings explicitly. The phrasing is specific enough that an agent can identify the tool's role.

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

  Usage Guidelines2/5

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

  The description offers no guidance on when to use this tool versus its siblings (e.g., get_edition, get_feed). The constraints 'Public newspaper only' and 'Do not fetch Hopper' are behavioral restrictions, not usage routing. It does not mention alternatives or conditions under which another tool should be chosen.

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

• get_robotsB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries full disclosure burden. It mentions the HTTP method and source, but does not clarify read-only behavior, response format, or any potential side effects. The phrases 'Not tax advice' and 'Headlines may be outbound' are nonstandard and do not communicate typical operational traits.

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

  Conciseness3/5

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

  The core instruction is front-loaded and clear, but the inclusion of 'Not tax advice' and 'Do not fetch Hopper' adds irrelevant or ambiguous content that could distract the agent. It is short, but not optimally lean.

  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, no-parameter GET endpoint, the description sufficiently identifies the resource and scope. Although it omits expected return structure, the purpose (robots.txt) makes that implicit, and the provided cautions are not critical.

  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?

  There are zero parameters, so the schema description coverage is 100% by default. The description adds no parameter details, but that is unnecessary as there are none; the baseline for zero parameters is 4.

  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 ('GET /robots.txt') and the resource ('from the public newspaper'). It is distinct from sibling tools which target other resources like editions or feeds, and the method and path are explicit.

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

  Usage Guidelines2/5

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

  While it emphasizes 'Public newspaper only' and 'Do not fetch Hopper', it does not provide explicit guidance on when to use this tool versus siblings (e.g., get_edition, get_feed). The conditions for choosing an alternative are absent.

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

• get_editionA
  3.7/5.0
  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 that it is a GET request, that it returns the current paper, and notes that headlines may be outbound. However, it does not describe response format, error conditions, or rate limits, which remain unknown for this endpoint. The scope constraint 'Public newspaper only' is stated, but overall behavioral information is sparse.

  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 and front-loaded with the main action (GET /edition.json from the public newspaper). The extra clauses like 'Not tax advice' and 'Do not fetch Hopper' add contextual warnings but are short and do not bloat the text. Every sentence contributes to understanding the tool's purpose and constraints, though one could argue the 'Not tax advice' is somewhat extraneous.

  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 zero-parameter GET endpoint with no output schema, the description provides the essential information: the endpoint, scope, and a behavioral caveat about outbound headlines. It does not detail expected response structure or error handling, but for such a simple tool, this level of detail is largely sufficient. The description is complete enough for an agent to decide to call it.

  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 tool has zero parameters and an empty input schema, so the description carries no parameter-explanation burden. With schema coverage at 100% (since there are no parameters to cover), the baseline score of 4 is appropriate. The description does not add parameter details because none exist.

  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 HTTP method (GET), the resource (/edition.json), and the scope (public newspaper, current paper). It also distinguishes from potential alternatives by specifying 'Public newspaper only' and explicitly warning 'Do not fetch Hopper,' which clarifies the tool's specific target.

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

  Usage Guidelines2/5

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

  The description gives no explicit guidance on when to use this tool versus its siblings. It implies usage for fetching the current edition, but the only exclusion is 'Do not fetch Hopper,' which is not a sibling tool. No mention is made of alternative tools like get_feed or get_llms_txt, or conditions that would choose one over the other.

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

• get_feedA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral burden. It discloses that 'Headlines may be outbound' and includes an instruction 'Do not fetch Hopper,' adding some context. However, it does not describe response format, pagination, errors, or safety profile, leaving significant gaps for a read operation.

  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 short and front-loads the core action (GET /feed.json). However, 'Not tax advice' is gratuitous and does not earn its place, slightly detracting from overall conciseness.

  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 simple parameterless GET endpoint, the description is adequate but not complete. It hints at content ('headlines') and includes warnings, but lacks details like authentication requirements, rate limits, or expected response structure. Given no output schema, more explicit return info would help.

  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 tool has zero parameters, so schema coverage is trivially 100%. Per the rubric, a baseline of 4 applies. The description adds no parameter-specific details because there are no parameters to document.

  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: 'GET /feed.json from the public newspaper.' It specifies the resource and source, and 'Public newspaper only' further narrows scope. This distinguishes it from sibling endpoints like get_edition or get_best_of_the_rest, even without naming them.

  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?

  Provides a clear context ('public newspaper only') and a specific exclusion ('Do not fetch Hopper'), but does not explicitly mention when to use this tool versus alternatives. The guidance is implied rather than stated, leaving some ambiguity about choosing among siblings.

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