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

Annotations already flag destructiveHint=true, so the bar is lower, but the description adds real context: the effect is immediate, it applies across both REST and MCP surfaces, it is scoped to the caller's own account, and self-revocation is permitted and terminates the caller's own access. The main undisclosed behaviors are whether revocation is reversible and what happens when the id is unknown or already revoked.

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?

Three short sentences, zero filler, with the most consequential fact (immediate, cross-surface shutdown) front-loaded and the dangerous self-revocation case called out last where it is most salient.

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?

A rich output schema and explicit destructive annotations carry much of the load, and the description covers consequences and eligibility well. However, for a single-parameter destructive tool where the sole parameter is completely undocumented in the schema, the description leaves the agent without any guidance on supplying the id.

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% and the single required parameter 'id' is never mentioned in the description. The text refers to 'the key you are calling with' and 'keys on your own account', which gestures at key identification, but an agent gets no confirmation that the parameter is a UUID, nor any guidance on where the id comes from.

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 the concrete effect of the operation: 'The key stops working at once, on REST and MCP.' Combined with the title this makes the verb (revoke) and resource (an API key) unambiguous, and the scope note 'Only keys on your own account' separates it from sibling operations like list_keys or create_key. It never restates the verb 'revoke' itself, relying on the title for that, which keeps it just short of a 5.

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 eligibility constraint ('Only keys on your own account can be revoked') and a clear precondition for the edge case of self-revocation ('make a new key first if you need one'). Missing is any routing hint for how to obtain the key id (e.g., pointing at list_keys) or what to do if the key is already revoked, so it stops short of full when/when-not coverage.

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