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

Annotations only supply the boolean profile (readOnly=false, destructive=false, idempotent=false); the description goes well beyond them by stating the blast radius: the key can no longer be exchanged at `agentAuth`, its MCP event subscriptions stop, but an already-minted session lives out its `id_token` hour. It also discloses that re-revoking an already-revoked key succeeds as a no-op and that the call is free, which is exactly the operational context an agent needs before mutating state.

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 front-loaded with the action and effects, and nearly every sentence carries distinct information (equivalence, effects, session survival, idempotence, alternative, cost). The heading-plus-first-sentence repetition of 'Revoke an API key' and the RFC citation are mild padding, keeping it just short of a 5.

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 single-parameter mutation with an output schema present, everything the agent needs is covered: what is revoked, what stops, what survives, what happens on repeat calls, and the alternative endpoint. Return-value details are correctly left to the declared output schema.

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 single `keyId` parameter is fully documented in the schema, including its source (`createAgentApiKey` / `listAgentApiKeys`) and an example value. The description adds no format or syntax detail beyond that (it only implies which identifier the alternative path avoids), so the baseline 3 is correct.

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 opens with a specific verb and resource ('Revoke an API key') and immediately disambiguates it from the create/list key siblings by naming the `lasoak_` key format and equating the action to the dashboard's Revoke. An agent can place it precisely among create_agent_api_key, list_agent_api_keys, and exchange_api_key.

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 explicitly routes the agent: use this tool with a `keyId`, or POST the raw token to `/oauth/revoke` (RFC 7009) if you already hold the value and don't want to look up its id. That is a concrete when-to-use-this-vs-alternative condition rather than vague context.

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