tap_doctor

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

Annotations declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds beyond this by detailing the return structure, the expensive nature of unscoped checks, and the recursive diagnosis for pipe taps via body.children, all consistent with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is composed of four well-structured sentences, each serving a clear purpose: purpose, output, usage scenarios with warnings, and special handling for pipe taps. No extraneous information.

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

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

Given the tool's complexity, the description covers all necessary aspects: when to use, what to expect (return structure with annotations), behavioral warnings (unscoped cost), and alternative tools (tap.explain). The absence of an output schema is compensated by the detailed return format description.

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

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

Schema description coverage is 100%. The description adds behavioral context for the 'site' and 'name' parameters, such as the cost of omitting them (scanning all user taps), but does not elaborate on the 'timeout' parameter beyond what the schema provides (default value).

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

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

The description explicitly states it is a health check for taps, runs examples against a health contract, and returns a structured response. It distinguishes itself from sibling tools like tap_run and tap_explain by mentioning that tap.explain is for static analysis without running.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear when-to-use scenarios: when tap.run returns empty/error rows or after forge.save to validate. It warns against unscoped scans and recommends always specifying site+name, and explicitly mentions tap.explain as an alternative for static analysis.

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