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

Goes well beyond the annotations: it warns that the old code stops working at once (confirming destructiveHint), that the new code is displayed exactly once and must be captured, that the key itself is unchanged, and that loss is unrecoverable. The one thing left implicit is whether the response is the only place the new code appears, though 'shown this once' effectively covers it.

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, no filler. The trigger condition comes first, followed by consequences, and each sentence carries distinct information the agent needs before calling.

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?

There is no output schema, and the description compensates by stating that the new code is returned once and only once. Combined with the irreversibility warning, an agent has everything needed to call this correctly and to preserve the result.

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 50% schema description coverage, the description is carrying real weight: it tells the agent to pass the existing code as recovery_code, which the schema leaves undocumented. The key parameter's own schema description is already thorough, so the description sensibly does not repeat it beyond noting it travels along.

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 and resource: issue a replacement recovery code. The action and its outcome are unmistakable. It doesn't name a sibling tool, but no sibling (register, signup, unregister) offers anything comparable, so disambiguation is not a real risk.

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 explicit trigger condition — use it 'if the one you have may have been seen' — and an explicit non-use case: a lost code cannot be replaced, so this tool is not a recovery path. Both when and when-not are stated directly.

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