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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's extra job is to add context — and it does: it discloses the cascade effect (all keys are revoked too) and the auth scope required. It stops short of stating that revocation is permanent or what happens to existing sessions.

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, front-loaded with the action and its blast radius, followed by the permission requirement. Nothing redundant.

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 low-complexity two-parameter destructive mutation with no output schema, the description covers the action, the cascade, and the permission. Only permanence/irreversibility and failure behavior are unstated.

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 50%: idempotency_key is well documented in the schema, while agent_id carries only a format hint. The description implies the target is an agent but adds no detail on where to obtain the ID or what an invalid ID does, so it only partly compensates for the gap.

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?

States a specific verb ('Revoke') and resource ('an agent') and adds scope ('and all of its keys'), which no sibling tool does. It is trivially distinguishable from create_agent and list_agents.

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 names the required scope 'agents:manage', which is a useful precondition for invocation. However, it gives no guidance on when to prefer this over alternatives, no warning that revocation is irreversible, and no note that the identifier typically comes from list_agents.

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