Server Quality Checklist

Tool Scores

• get_test_recommendationA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses that the tool returns a URL and details, but does not describe error behavior, auth requirements, or the structure of 'details'. As a simple read operation, this is acceptable 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 a single clear sentence with no unnecessary words. It front-loads the action and resource, making it instantly scannable.

  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 getter tool, the description is nearly complete. It indicates what will be returned (test URL and details), and the sibling tools provide context. However, without an output schema, a bit more detail about the 'details' structure would make it fully 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% and the single parameter bias_id is well-described with an example. The description's mention of 'by its ID' aligns with the parameter but adds no extra meaning beyond the schema, earning the baseline score of 3.

  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 'Get' and the resource 'test URL and details for a specific cognitive bias by its ID'. It distinguishes itself from sibling tools like get_supported_biases (which lists biases) and analyze_text_for_bias (which analyzes text) by focusing on retrieving a test recommendation for a given bias ID.

  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 when a bias ID is known and you need its test URL/details, but it does not explicitly mention when to avoid this tool or consider alternatives. Sibling names provide context but are not referenced, so guidance on choosing between tools is only implicit.

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

• analyze_text_for_biasA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the transparency burden. It indicates a read-only analysis action ('analyzes', 'suggests') and no side effects are implied, but it does not disclose output format, limitations, or any processing details beyond the basic function.

  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, front-loaded sentence with no redundant wording. Every element ('analyzes', 'given text', 'suggests cognitive biases', 'core diagnostic engine') adds meaningful 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 simple one-parameter tool with no output schema, the description sufficiently explains the tool's purpose and provides input examples. It could be more detailed about the exact return format (e.g., list of biases with explanations), but the phrase 'suggests which cognitive biases might be present' gives a reasonable indication.

  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 provides a clear description of the 'text' parameter (100% coverage), and the tool description adds semantic depth by offering examples of what constitutes valid input (argument, decision, belief). This goes beyond the schema's generic phrasing.

  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 uses a specific verb ('analyzes') and resource ('text') and clearly states the output ('suggests which cognitive biases might be present'). It distinguishes itself from sibling tools like get_supported_biases (which lists biases) and get_test_recommendation (which recommends tests) by framing itself as the core diagnostic engine.

  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 this is the primary tool for bias analysis ('core diagnostic engine function') and gives examples of appropriate inputs (argument, decision, belief). However, it does not explicitly contrast with sibling tools or state when to use it instead of get_supported_biases or get_test_recommendation.

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

• get_supported_biasesA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden of safety. It explicitly states the tool returns a list, conveying a read-only, non-destructive operation. It adds meaningful context about the scope ('all cognitive biases') but doesn't detail error behavior or format, which is acceptable for a simple list endpoint.

  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, front-loaded sentence with no filler. Every word earns its place, efficiently conveying the tool's purpose and scope.

  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's simplicity (no parameters, no output schema, no annotations), the description fully covers what an agent needs to know. It clearly states what is returned and the scope, making it complete for this context.

  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 input schema has zero parameters, so the baseline is 4. The description does not need to explain parameters, and the empty schema is self-explanatory.

  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 uses a specific verb ('Returns') and resource ('list of all cognitive biases'), clearly distinguishing it from sibling tools like analyze_text_for_bias and get_test_recommendation. It states exactly what the tool provides.

  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—one would call this to discover supported biases before analysis—but it does not explicitly mention when to use this tool versus the siblings or any exclusions. Usage is clear by inference, but not directly stated.

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