Server Quality Checklist

Tool Scores

• list_improvementsA
  4.6/5.0
  Behavior5/5

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

  The description adds substantial behavioral detail beyond the annotations: ordering by priority, inclusion of open and completed items, default preference for open items, interpretation of empty results, formatting of enum labels for humans, and the setup-guidance fallback when no website exists. This goes far beyond the read-only and idempotent hints, providing comprehensive behavior for edge cases.

  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 relatively long but every sentence adds value: it covers purpose, ordering, statuses, default behavior, empty results, formatting, and the setup fallback. It is front-loaded with the core purpose and maintains a logical flow. While not minimal, the length is justified by the range of behavioral nuances it conveys.

  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?

  Given the tool has no parameters, an output schema exists, and annotations declare safety, the description is complete. It explains what the tool returns, how to interpret results, special cases (empty list, no website), and formatting guidelines. Nothing an agent needs to call it correctly is missing.

  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 does not need to explain parameter meaning. The schema coverage is 100% (vacuously). The description adds context about output fields like status and impact, but since there are no parameters, the baseline of 4 applies without further enhancement needed.

  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 a specific verb ('List') and resource ('content improvements for the account website'), with additional detail on ordering by product priority. This distinguishes it from sibling tools like list_topics or list_competitors, as it targets improvement recommendations rather than generic content lists.

  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 usage guidance: 'Prefer open items unless the user asks for completed work' and 'When the user asks what to improve, lead with these product recommendations before any extra strategy.' It does not explicitly name alternatives, but the context is sufficient for an agent to decide when to invoke it, especially given the distinct purpose.

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

• get_visibilityA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to repeat these. It adds valuable behavioral context beyond annotations by describing the no-website scenario (returns setup guidance and empty payload) and explicitly warns against fabricating dates/scores. This enriches the agent's understanding of potential response variations.

  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 with no filler. It front-loads the core purpose, then provides usage guidance, and finally covers the edge case. Every clause serves a purpose, and the structure flows logically from what → when → special condition. It is concise and well-organized.

  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?

  Given zero parameters and a defined output schema, the description covers everything needed to invoke the tool correctly: purpose, usage context, and the special no-website behavior. It also preempts hallucination by instructing the agent not to invent dates or scores. Nothing essential is missing for a safe and correct call.

  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 baseline is 4. The description doesn't need to explain parameters since there are none. It doesn't add anything specific about parameters, but that's expected—the schema is empty and the description focuses on the operation and response behavior.

  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: 'Get overall AI visibility for the account website' and specifies the exact outputs (visibility score, delta, insight). It explicitly distinguishes itself from siblings by positioning it as a 'high-level snapshot before drilling into topics, prompts, or competitors,' which unambiguously differentiates it from list_topics, list_prompts, etc.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: 'Use this for a high-level snapshot before drilling into topics, prompts, or competitors.' It also covers the edge case when no website is configured, directing the agent to follow server instructions rather than inventing data. This is actionable and clear.

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

• list_competitorsA
  4.7/5.0
  Behavior5/5

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

  Annotations already mark the tool read-only, idempotent, and non-destructive, and the description adds substantial behavior: up to 8 rows, appended rows for the owned website and brand ahead, non-strict ordering, and the no-website setup payload with an instruction not to invent dates or scores.

  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 dense but every sentence earns its place: it front-loads the core purpose, then covers ordering behavior, comparison preference, and the no-setup edge case without redundant wording.

  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?

  With no parameters and an output schema present, the description fully covers the normal call flow and the notable no-website edge case. Nothing essential for an agent to invoke the tool correctly is missing.

  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 and the input schema is fully described, so there is nothing for the description to add. The baseline of 4 applies because parameter semantics are not relevant here.

  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?

  Clearly states the tool lists the visibility leaderboard for the account website with share-of-voice metrics. The verb and resource are specific, and the 'competitor leaderboard' framing distinguishes it from sibling list_* tools 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 Guidelines4/5

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

  Provides operational guidance: prefer visibilityRank, then share of voice; highlight isKeyCompetitor rivals; follow server instructions when no website is set up. It does not explicitly contrast with siblings, but the leaderboard context and comparison guidance make the intended use clear.

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

• list_promptsA
  4.8/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable edge-case behavior: the response when no website is set up (setup guidance with empty payload) and the instruction not to invent dates or scores. This goes beyond the structured annotations and gives the agent concrete handling steps.

  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 dense paragraph that front-loads the core purpose, then gives usage guidance and edge-case behavior. Every sentence contributes value, but it is slightly longer than strictly necessary, mixing guidance with edge-case instructions. It is still well-structured and not verbose enough to lose a point below 4.

  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?

  Given the tool has no parameters, an output schema, and annotations covering safety, the description is complete. It explains what data is returned, how to interpret it, when to use it, how to handle topic naming, and the no-website edge case. Nothing an agent needs to call it correctly is missing.

  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 correctly omits parameter details. The baseline of 4 applies because there is nothing to add; the description does not waste space on non-existent parameters. It fully covers the absence of parameters without redundancy.

  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 verb 'List' and the resource 'tracked prompts' along with the specific data returned (visibility metrics, parent topicId, mentioned flag, per-prompt competitors). It distinguishes itself from sibling tools like list_topics by specifying the added competitor and metric details, so an agent can immediately tell them apart.

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

  Usage Guidelines5/5

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

  Explicitly instructs to 'Prefer after list_topics when you need specific query-level detail', naming the alternative and the condition. It also provides concrete guidance on matching topicId to list_topics and using the returned prompts array length for gap counts, leaving no ambiguity about when and how to use this tool.

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

• list_topicsA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds non-obvious behavioral context: list order is not importance, promptCount may exceed list_prompts rows, and a missing website returns setup guidance with an empty payload. This prevents misinterpretation and hallucination.

  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?

  Every sentence earns its place: payload contents, ordering caveat, count semantics, sibling routing, and the no-website edge case. The description is dense but free of filler and front-loads the core purpose.

  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 zero-parameter read-only tool with an output schema and safety annotations, the description covers all needed caveats and the failure mode. Nothing essential is missing for an agent to select and call it correctly.

  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 there is no parameter documentation burden on the description. The baseline of 4 applies because the description instead clarifies output semantics and field meanings.

  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 ('List') and resource ('topic rollups for the account website'), and enumerates the exact fields returned. It clearly differentiates itself from list_prompts by naming per-prompt detail as a separate purpose.

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

  Usage Guidelines5/5

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

  It explicitly tells the agent to use list_prompts when per-prompt detail or coverage-gap counts are needed, implying list_topics for rollups. It also warns that list order is not importance order and gives setup-edge-case handling instructions.

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