Server Quality Checklist

Tool Scores

• audit_pricingA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds useful context about what the tool returns: price, turnaround, manual verification details, and a Stripe checkout URL. It also states 'No arguments,' clarifying invocation behavior beyond the schema.

  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?

  A single dense sentence communicates the audit scope, review process, output contents, and parameter requirements without waste. Every phrase adds meaning, and the most important information is front-loaded.

  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-argument informational tool with read-only, idempotent annotations and no output schema, the description is fully sufficient. It tells the agent what the tool will describe and what content to expect, leaving no missing invocation details.

  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?

  With zero parameters and 100% schema description coverage, there is little for the description to add. It explicitly confirms 'No arguments,' which fully resolves parameter ambiguity and aligns with the empty input 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 uses a specific verb ('Describe') and names a concrete resource ('Project Feldspar's paid code audit'), then enumerates exactly what is covered: scope, price, turnaround, and Stripe checkout URL. It clearly distinguishes itself from the sibling scan_repository, which would perform scanning rather than provide audit-pricing information.

  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 title and description make the intended use clear: retrieve information about the paid audit offering and how to order it. However, it does not explicitly mention when not to use it or contrast it with scan_repository, so the guidance is implied rather than stated.

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

• scan_repositoryA
  4.5/5.0
  Behavior5/5

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

  The description adds substantial behavioral context beyond the annotations: it clones a repository, runs a deterministic scan with no LLM involvement, reports secret findings with redacted evidence, and may take 2–90 seconds. It also explains the output format, which is essential since there is no output schema. No contradiction with readOnlyHint=true or openWorldHint=true.

  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 information-dense yet well-structured: it front-loads the core action, provides a parenthetical list of supported lockfiles, and covers output, determinism, and timing in a single compact paragraph. Every sentence contributes value.

  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 single-parameter tool with no output schema, the description is fully complete. It explains inputs, scanning scope, output structure, determinism, lack of LLM involvement, supported repository hosts, secret redaction, and expected runtime. There is no gap that would prevent correct invocation.

  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 description coverage is 100% because the sole parameter url includes a description with supported host examples. The description does not add meaning beyond the schema—it only mentions the URL implicitly through 'public git repository'. Baseline 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 uses a specific verb and resource: 'Clone a public git repository and run feldspar-scan' with a clear enum of what it scans and what it returns. It is distinguishable from the sibling audit_pricing tool because it uniquely mentions repository scanning, lockfile dependency advisories, secrets, and config lint.

  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 clearly establishes what the tool does and its operational context: public git repositories from supported hosts, deterministic behavior, and 2–90s runtime. It does not explicitly state when not to use it or mention alternative tools, but the context is sufficient for an agent to decide when it applies.

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