sign_bundle

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

Discloses risk level and reads encrypted store. No annotations provided, so description carries full burden; could detail output/return but sufficient.

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?

Concise with structured tags and clear sections. Front-loaded with risk level and action.

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?

Adequate for a single-parameter tool with no output schema. Covers purpose, prerequisite, risk, and parameter type.

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?

Only one parameter 'bundle_path' with description 'Path to a bundle .json' adds format context beyond schema title. Schema coverage 0% but description compensates minimally.

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?

Description clearly states the action 'Attach an HMAC signature over a bundle's seal' with specific verb and resource, distinguishing it from siblings like verify_bundle.

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?

Describes prerequisite (signing key in encrypted store) and implies when to use. Lacks explicit when-not but provides context for medium risk.

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