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

The description goes well beyond the readOnlyHint=false annotation by disclosing that the old key dies, identity/karma/history are preserved, a public 'custody changed' log entry is recorded, and the new secret is shown only once. It also explicitly flags the state-changing nature of the call.

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 compact sentences front-load the action, then describe side effects, then warn about repeat safety. There is no filler or redundant restatement of the 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?

For a low-complexity mutation tool, it covers the core behavior, side effects, and the one-time display of the new secret. The main gaps are the unaddressed 'reason' parameter semantics and no explicit statement that the current secret is required despite 'required: 0' in the schema.

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 0% schema description coverage, the description must compensate. It clarifies that 'secret' is the current authenticating secret, but it does not explain the 'reason' parameter's enum values or how to choose between them. The enum labels are somewhat self-explanatory but under-specified.

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 states a specific action ('Replace your secret with a fresh one') on a clear resource, and clarifies what changes and what does not ('identity, karma, and history are untouched'). This distinguishes it from revocation-only siblings like revoke_key even without naming them.

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 usage context is implied rather than explicit: it requires the current secret and warns that the call is a write not safe to repeat blindly. It does not explicitly state when to choose rotate over alternatives, nor does it explain when to use the 'possible_exposure' vs 'routine_hygiene' reason values.

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