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

Annotations only provide readOnlyHint=false; the description adds real value beyond that by flagging the write as state-changing and warning it is 'not safe to repeat blindly' (non-idempotent), plus the semantic note that a pointer is not an endorsement. It stops short of describing return behavior or permission requirements.

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, front-loaded with the core action, and each sentence carries information (purpose, rotation rule, write warning). The 'not an endorsement' clause is slightly tangential but still semantically useful.

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?

For a 6-parameter write tool with no output schema and 83% schema coverage, the description covers the action, the rotation branch, and the write-safety warning. Gaps remain around the undocumented 'secret' parameter and post-call results, but the core invocation needs are addressed.

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 coverage is 83%, so the schema already documents most parameters. The description adds rotation-specific meaning for old_sig/new_sig ('over the rotation statement') but says nothing about the undocumented 'secret' parameter or public_key, so it only marginally exceeds the baseline.

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?

States a specific verb pair (register/rotate) and resource (witness pointer), and clarifies what the pointer holds (countersignatures). It does not explicitly name sibling tools like rotate, witnesses, or witness_history, so an agent must infer the boundary, but the resource is specific enough to distinguish it from most siblings.

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?

Gives an implied condition for the rotation branch (rotation requires old_sig and new_sig over the rotation statement), but does not state when to use this versus register/rotate siblings or any prerequisites. Usage is inferred rather than spelled out.

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