Server Quality Checklist

Tool Scores

• mentions_compareC
  2.2/5.0
  Behavior2/5

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

  Annotations indicate readOnlyHint=true and openWorldHint=true, but the description adds little beyond 'compute the delta.' It fails to disclose the input contradiction (OR vs AND) or any other behavioral 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?

  Two sentences with no fluff, but the first sentence is misleading regarding input combination, reducing its value.

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

  Completeness2/5

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

  No output schema, no mention of return format, pagination, or error handling. The description is too sparse given the tool's complexity and parameter count.

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

  Parameters1/5

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

  With 0% schema description coverage, the description should explain parameters. It only vaguely mentions 'two queries OR two brands' but does not cover the required combination, optional parameters, or the mode enum.

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

  Purpose3/5

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

  The description states it computes delta between two queries or two brands, which is a specific purpose. However, the required fields (query_a and brand_a) suggest both are needed, contradicting the 'OR' implication. This reduces clarity.

  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?

  Mentions 'competitor analysis' as a use case but provides no guidance on when to use this tool versus siblings like mentions_check, mentions_discover, or mentions_watch.

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

• mentions_discoverB
  3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, indicating safe, non-destructive behavior with potentially incomplete results. The description adds that output is '~50 candidate queries' and spans specific intents, slightly enhancing transparency.

  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?

  Two concise sentences that front-load the purpose ('suggest queries to track for a given brand') and add a detail about output volume and intent types. No extra or redundant information.

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

  Completeness2/5

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

  With 3 parameters, no output schema, and 0% schema description coverage, the description is too sparse. It omits details on optional parameters and output structure, forcing the agent to guess or rely on tool name.

  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 has 0% description coverage, so description must explain all parameters. It only hints at 'given brand' for the required parameter. Industry and count parameters are not described, leaving their roles ambiguous.

  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 suggests queries to track for a brand and specifies the output includes ~50 candidates across informational, commercial, and comparison intents. It does not explicitly distinguish from sibling tools like mentions_check or mentions_compare, but the name and verb 'discover' imply its unique 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?

  No guidance on when to use this tool versus siblings (mentions_check, mentions_compare, mentions_watch). The description does not mention alternatives or constraints, leaving the agent to infer usage from context.

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

• mentions_watchB
  3.3/5.0
  Behavior4/5

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

  Annotations indicate readOnlyHint=false (write), destructiveHint=false, and openWorldHint=true. The description adds behavioral context by specifying that the tool sets up a persistent monitor that sends webhooks on changes, which goes beyond the title. It does not contradict annotations.

  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 description is a single 15-word sentence, which is concise and front-loaded with the core purpose. However, given the tool's complexity (7 parameters, webhook setup), the description could earn its place better by adding parameter guidance without becoming overly long. It is minimally adequate.

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

  Completeness2/5

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

  With 7 parameters, no output schema, and the expectation of webhook configuration, the description lacks critical details such as parameter semantics, return value (e.g., monitor ID), and behavior on duplicate monitors. The agent would struggle to use this tool correctly without additional context.

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

  Parameters1/5

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

  The input schema has 7 parameters with 0% description coverage. The main description does not mention or explain any parameter's purpose, default value, or constraints (e.g., 'query' vs 'brand', 'mode' enum options). This leaves the agent without guidance for filling parameters correctly.

  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 sets up a persistent monitor that webhooks on changes to brand mentions, ranks, or citations. It uses a specific verb ('set up') and resource ('persistent monitor'), and the outcome is explicit. This distinguishes it from siblings like mentions_check (one-time check) and mentions_compare (comparison).

  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 usage for continuous monitoring through phrases like 'persistent monitor' and 'webhooks you when...change,' but it does not explicitly state when to use this tool versus alternatives like mentions_check or mentions_discover. No exclusions or comparative guidance are provided.

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

• mentions_checkA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint. The description adds value by specifying the output structure (mentions, ranks, citations, fan-out queries, brand entities) and disclosing pricing and cache behavior. No contradictions with annotations.

  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 concise for the amount of detail, with the purpose stated upfront. The list of modes is thorough, but the single-paragraph structure could be more scannable (e.g., bullet points). No redundant sentences.

  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?

  Without an output schema, the description adequately explains return values. It covers most operational aspects (modes, pricing, output contents). However, it does not fully detail all parameters or prerequisites, leaving some gaps for complex usage.

  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 description coverage is low (33%). The description only adds meaningful context for the 'mode' parameter, explaining each option. Parameters like providers, runs, and region receive no explanation, leaving the agent without guidance despite low schema coverage.

  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 tool checks brand mentions across AI search surfaces, listing 8 specific modes with costs and behavior. This clearly distinguishes it from sibling tools (mentions_compare, mentions_discover, mentions_watch) by focusing on checking current mentions.

  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 detailed guidance on when to use each mode (e.g., quick for cost efficiency, live modes for ground-truth citations) and includes pricing. However, it does not explicitly contrast with sibling tools or state when not to use this tool, which would improve the score.

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