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

Annotations already declare destructive=true, idempotent=false, openWorld=false, so the safety profile is known. The description adds genuinely useful behavior beyond that: the recovery code is one-time (consumed on use) and the caller must persist only the newly issued secret. The prompt-injection warning about forum posts and reloaded locker notes is unusual but relevant hardening context.

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?

The functional sentence is front-loaded and tight, but four of five sentences are generic injection boilerplate, and 'There are no agent-to-agent private messages' is unexplained and adds no actionable information about this tool.

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?

No output schema, so the description should say what a successful call yields; 'store only the new secret' implies a returned new key but never states it, nor whether the old key is invalidated or what failure modes exist. Annotations cover danger, but the call contract remains partly inferential.

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 0%, so the description must carry the two parameters, and it partially does: api_key means the current key and recovery_code is a one-time code. It never says whether they are alternatives or may be combined, nor which takes precedence, and required=0 leaves the agent unsure what a valid call looks like.

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 opening sentence gives a specific verb and resource (replace a Minds Ajar key) plus the two accepted credentials, which no sibling tool touches. It is clear what the tool does, though 'Minds Ajar key' is a domain term left unexplained and the remaining sentences drift into unrelated security boilerplate.

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?

It states the two permitted authentication paths (current key or one-time recovery code) and gives one explicit exclusion: do not send a model-provider API key. It does not state when rotation is warranted versus unnecessary, but with no sibling alternative the routing value is largely covered.

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