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

The description adds real behavioral detail beyond the annotations: deletion is immediate (no grace period) and a confirmation token is required, implying a two-step CONFIRMATION_REQUIRED flow. But it directly conflicts with the annotation destructiveHint=false — permanently invalidating a credential is destructive, and an agent reading the annotations could invoke this without the caution the description implies.

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?

Two short sentences with the destructive action and the key prerequisite front-loaded; nothing is padded. It is arguably over-terse rather than wasteful, which is penalized elsewhere rather than here.

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 an irreversible credential-destroying mutation with no output schema, the description never explains the confirmation flow mechanics, what happens to in-flight requests using the revoked key, whether the action can be undone, or how it differs from rotate_api_key. Combined with the destructiveHint=false conflict, an agent lacks what it needs to call this safely.

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 100%, so all three parameters are already documented, including that confirmToken comes "From the CONFIRMATION_REQUIRED reply." The description's "Needs a confirmToken" usefully implies the token is conditionally mandatory even though the schema marks only keyId as required, but it says nothing about organizationId.

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?

"Deletes a key immediately" gives a specific verb (delete) and resource (an API key, per the name), which is enough to tell it apart from create_api_key, rotate_api_key and list_api_keys. It stops short of explicitly naming the sibling it replaces, but the action is unambiguous.

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?

"Needs a confirmToken" signals a prerequisite and implies the confirmation flow, which is useful usage context. However, there is no guidance on when to revoke versus rotate a key, no statement about who may call it, and no mention of the org-scoped variant (organizationId) or what to do when the token is absent.

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