tap_fix

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

Description adds context beyond annotations: tier limitations (free vs Pro), output shape (diagnostics + patches), and that it runs tap.doctor first. Annotations declare readOnlyHint=true and destructiveHint=false, and the description aligns (no claim of actual mutation). No contradiction.

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?

Four sentences, front-loaded with main action, no fluff. Every sentence adds value: purpose, procedure, return shape, tier info, usage condition. Efficient and clear.

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?

Covers purpose, procedure, return shape, and tier limitations. Missing error handling details (e.g., what if tap.doctor fails) but otherwise complete for a tool with 3 params and no output schema. Annotations and schema are present, so overall context is good.

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 has 100% coverage with descriptions for all three parameters. Description adds minimal extra meaning beyond mentioning 'site' and 'name' contextually. Baseline at 3 is appropriate since schema already handles parameter definition.

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 clearly states 'Diagnose and repair a broken tap' with specific actions (runs tap.doctor, collects diagnostics). It distinguishes itself from sibling tools like tap_doctor (which likely only diagnoses) and tap_run (which runs taps). The verb+resource combo is clear.

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?

Explicitly says 'Use when tap.doctor returns verdict=broken', providing a clear condition for use. It does not explicitly mention when not to use or alternatives, but the condition is direct and useful for the agent. Slightly better than vague hints.

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