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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered by structured data. The description adds only the underlying DELETE endpoint, which reinforces destructiveness but says nothing about what happens to existing sessions using the key, whether revocation is reversible, or what the error state looks like.

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 action front-loaded and no filler. The endpoint string is partially redundant with the tool name, which keeps it just short of ideal.

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 destructive credential mutation the description is thin: it does not mention that the call is gated on confirm=true, nor the consequence of revoking the last active key. Rich annotations and a fully documented schema compensate enough that an agent could still invoke it correctly, but the description itself is only minimally sufficient.

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 100% and the confirm parameter is documented in detail there, so the schema does the heavy lifting. The description contributes no additional meaning about organization_id or api_key_id formats, which is acceptable at full coverage but adds no value.

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?

"Revoke an API key" pairs a specific verb with a specific resource, and the endpoint line confirms it is a DELETE on an org-scoped key. It does not distinguish itself from near-neighbours such as keys.get, addon.status or ai.keys, so an agent must infer the boundary from the name alone.

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?

There is no statement of when to revoke versus rotate or inspect a key, no precondition (ownership/admin rights), and no warning about irreversible credential loss. The confirm-gate exists only in the schema, so the description gives no routing or sequencing guidance whatsoever.

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