Server Quality Checklist

Tool Scores

• evaluate_fca_handbook_applicabilityA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses critical behaviors: the 90+ second runtime, streaming of progress messages, billing implications, the need to display progress messages, the nature of refinement_suggestions, and the explicit warning against speculation to avoid hallucination risk. This goes far beyond any annotation coverage.

  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 long but every section serves a purpose: purpose, critical warnings, pre-call guidance, parameter details, and post-call handling. It is well-structured with clear headings and critical caveats in block caps. It could be slightly condensed, but the length is justified by the complexity of behavioral quirks and usage requirements.

  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 complexity, lack of annotations, and absence of an output schema, the description covers virtually all necessary aspects: purpose, when to use, what to prepare, runtime behavior, progress messaging, billing, refinement_suggestions handling, and detailed parameter semantics. It even addresses hallucination risk and when to ask the user vs. re-call. No major gaps are evident.

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

  Parameters5/5

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

  The schema has 0% description coverage, but the description thoroughly compensates. For 'user_input', it explains the content, up to 5000 characters, and why all six elements matter. For 'analysis_mode', it explains the 'quick' vs 'full' options, time ranges, what 'full' does, and advises asking the user if unclear. It adds substantial meaning 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 'Evaluate which FCA Handbook entries apply to an entity' with a specific verb (Evaluate), resource (FCA Handbook entries), and scope (apply to an entity). It also names the specific system ('Metis FCA Handbook AI Harness'), which distinguishes it from any potential similar tools.

  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 states when to use the tool ('Use for questions about FCA authorisation, permissions, or obligations for a specific firm/product/service') and provides a detailed pre-call checklist of six required inputs, including when to ask the user for missing information. It also gives guidance on when to re-call the tool after receiving refinement_suggestions, covering both usage context and exclusions for thin input.

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