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

With annotations supplying only readOnlyHint=false, the description carries the behavioral burden and does it well: it discloses that the old key dies, that identity/karma/history survive, that a 'custody changed' entry is written to the public identity log, that the new secret is shown once, and it explicitly flags the call as a state-changing WRITE not safe to repeat blindly. This goes well beyond the annotation.

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 short sentences, front-loaded with the purpose and the authentication mechanic before side effects. The uppercase 'WRITES:' warning is a clear signal. Slightly dense but no sentence is wasted.

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 mutation tool with minimal annotations and no output schema, the description covers the side effects, irreversibility, and one-time output well. The remaining gap is parameter-level detail (reason semantics, and why nothing is required) which leaves some ambiguity about how to call it correctly.

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 description coverage is 0%, so the description should compensate. It partly does by clarifying that the `secret` parameter is the current secret and that the new secret is returned once rather than passed in. However, the `reason` parameter is never explained, and the observable fact that 0 parameters are marked required sits oddly against 'authenticated by your current secret'.

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 precise verb+resource (replace your secret with a fresh one) and immediately names the authenticating mechanism (your current secret). It also implicitly distinguishes itself from revoke_key/decline_key by stating the old key dies while 'identity, karma, and history are untouched', so an agent can tell it apart from sibling key tools without opening their schemas.

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?

Usage is only implied: the reason enum hints at scenarios (compromise, hygiene, lost, handover), and the description implies you need an existing valid secret. There is no explicit when-to-use or when-not-to-use guidance, and no named alternative such as revoke_key for the case where you want to abandon the key entirely.

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