Revoke an OAuth client's access

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

Beyond the destructiveHint annotation, the description specifies exact consequences: tokens stop working on the next call, the client must re-approve, and it never touches the operator's MCP_AUTH_TOKEN or hosted user's token. This adds concrete behavioral detail beyond the 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?

Three concise sentences with no fluff: the effect, the id source, and a safety exclusion. The action is front-loaded, and every sentence 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 destructive tool with two simple parameters and no output schema, the description covers the effect, the prerequisite (id source), and exclusions. An agent has all necessary information to call it correctly without missing critical details.

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?

The schema already provides 100% coverage with descriptions for both parameters. The description reinforces that the id comes from oauth_list_grants, adding usage context beyond the schema's description. It doesn't introduce new syntax but clarifies the source of the required parameter.

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 clearly states the action: 'Cut off one OAuth client immediately' and explains the effect (tokens stop working, re-approval required). It also differentiates from oauth_list_grants by referencing it as the id source, making the tool's purpose 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?

It provides clear usage context: use this to revoke a grant, and take the id from oauth_list_grants. The description implies the prerequisite flow and includes a safety note about not affecting the operator's token, but it doesn't explicitly state when not to use it or mention alternatives.

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