Tap

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

Annotations indicate destructiveHint=true, but the description adds critical behavioral context not present in structured fields: specifically that it 'auto-commit to git' and reads from an internal 'forge.draft' state. This explains the side effects and data flow beyond what annotations provide. No contradictions with annotation flags.

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?

Three sentences with zero waste. First sentence defines the action, second explains input sourcing, third explains downstream usage. Every sentence provides unique value not redundant with schema or annotations.

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 (git integration, draft state management, disk I/O) and lack of output schema, the description adequately covers the tool's role in the ecosystem and its destructive nature. Could improve by mentioning conflict resolution behavior (e.g., what happens if the file already exists).

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?

With only 33% schema coverage (only 'code' has a schema description), the description partially compensates by explaining the 'code' parameter's semantics as an optional override to the default draft-reading behavior. However, it fails to clarify what 'site' and 'name' represent (paths? identifiers?), leaving two of three parameters semantically opaque.

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 the core action with specific verbs ('Save the draft tap to disk and auto-commit to git') and identifies the resource being manipulated. It effectively distinguishes from siblings by referencing 'forge.draft' (implying relationship with forge_draft) and contrasting with 'tap.run' (execution vs. persistence).

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?

Provides clear workflow guidance by stating 'Reads code from forge.draft — no need to pass code,' which establishes the prerequisite state. Also explains the optional override behavior for the code parameter and indicates the next step in the workflow ('tap.run can execute it'). Lacks explicit 'when not to use' guidance for 5/5.

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