Server Quality Checklist

Tool Scores

• free_search_advancedA
  4.1/5.0
  Behavior3/5

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

  No annotations provided, so description must fully disclose behavior. While it mentions 'quality control' and parameter min_confidence implies verification, it doesn't detail aspects like result ordering, rate limits, or output structure. Adequate but not comprehensive.

  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?

  Extremely concise: one sentence stating purpose, then bullet-like lists for best/not recommended. No wasted words, front-loaded with the core action.

  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?

  No output schema exists, so description should hint at return structure, but it doesn't. The tool's function (search results) is clear, but details like result format or pagination are missing. Adequate for basic use but incomplete for complex scenarios.

  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% with all parameters described. The description adds high-level context ('filters and quality control') but no additional meaning beyond what the schema already provides. Baseline score of 3 is appropriate.

  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 'Advanced search with filters and quality control' and distinguishes from sibling 'free_search' by specifying best for date ranges, domain filtering, high-confidence, Chinese content. It also explicitly says not for simple queries.

  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 ('Best for: Date ranges, domain filtering, high-confidence only, Chinese content') and when-not-to-use ('Not recommended for: Simple queries — use free_search instead'), directly referencing a sibling tool.

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

• free_extractA
  4.2/5.0
  Behavior3/5

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

  No annotations provided; description carries full burden. It discloses that output is clean markdown but does not mention rate limits, auth requirements, error handling, or behavior with non-text content. The transparency is adequate but lacks depth.

  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 extremely concise with four short sentences. It front-loads the core purpose, then adds usage guidelines without any superfluous words.

  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 no output schema and no annotations, the description covers the tool's purpose, input parameters, output format, and use cases. It could mention handling of unsupported URLs or errors, but for a simple extract tool, it is largely 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?

  Input schema already describes both parameters (url and max_length) with 100% coverage. The description adds no additional semantic meaning beyond the context of 'clean markdown,' so baseline score of 3 is appropriate.

  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 'Extract full content from a URL' and 'Returns clean markdown,' defining a specific verb and resource. It distinguishes from sibling tools by recommending it for specific pages found in search results.

  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 explicitly provides 'Best for' and 'Not recommended for' scenarios, advising against bulk extraction and directing to use 'search first' (referring to sibling tools). This gives clear when-to-use and when-not-to-use guidance.

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

• free_searchA
  4.4/5.0
  Behavior5/5

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

  Given no annotations, the description fully discloses behavioral traits: automatic fallback between free/paid engines, required API keys, deduplication, scoring, and ranking. This is comprehensive and leaves no ambiguity about the tool's 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 three concise sentences, front-loaded with the core purpose. Every sentence adds value: purpose, phases with requirements, and output behavior (deduplication, scoring, ranking). No extraneous information.

  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 3 parameters and no output schema, the description is fairly complete. It explains the fallback, engine requirements, and output quality. However, it does not describe the structure of the return value, which might require the agent to infer an ordered list.

  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 schema already describes 'limit' and 'engines' parameters, but the description adds context by mapping engines to phases and explaining free vs. paid. However, the 'query' parameter lacks additional semantic explanation beyond the schema.

  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 that the tool searches the web with automatic fallback between free and paid engines, and specifies the two phases and engines. It distinguishes itself from siblings by emphasizing the automatic fallback mechanism, which is a unique selling point.

  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 does but does not explicitly state when to use it versus the sibling tools 'free_extract' or 'free_search_advanced'. It lacks guidance on alternatives or when not 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.