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

Annotations already declare destructiveHint=true, and the description reinforces but also extends this with 'irreversible', clarifying that the operation cannot be undone. The warning about the MCP session's own key adds behavioral context beyond the annotations — it discloses a self-harm hazard specific to this tool. No contradiction exists between description and annotations.

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 description is a single compact sentence with two clauses: the operation and the crucial warning. Critical information (irreversibility, self-key hazard) is front-loaded, and there is zero filler. Every word earns its place.

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 simple one-parameter destruction tool, the description covers the endpoint, the irreversible consequence, and the most important hazard (revoking the session's own key). No output schema exists, but for a delete operation the return value is low-stakes. It is complete enough for an agent to invoke correctly, though it could optionally note what happens to active consumers of the revoked key.

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%, with the single parameter 'id' documented as 'UUID of the key to revoke'. The description's '{id}' placeholder merely echoes what the schema already states and adds no new semantic detail. Per the baseline rule for high-coverage schemas, a 3 is appropriate.

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 conveys action and resource via the REST shorthand 'DELETE /v1/agent/keys/{id}', making it clear the tool permanently removes an agent key. It distinguishes itself from sibling tools like create_key and list_keys through the explicit DELETE method and 'irreversible' qualifier. However, it relies on endpoint notation and the tool name rather than a plain-language verb-noun statement, so it stops 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?

The description provides a clear caution about when to avoid use ('Do not revoke the key used by this MCP session unless intentional'), which is valuable operational guidance. It does not explicitly state when this tool should be used or name alternatives, though no sibling offers equivalent functionality. The guidance is safety-oriented rather than decision-oriented, so it earns a mid-range score.

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