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

Adds substantial context beyond the annotations: the precise definition of 'unused', the guarantee that used keys are untouched, the dashboard equivalence, and the warning about freshly issued keys. The 'Free' note and the explicit blast radius are useful. The destructiveHint=false annotation sits slightly awkwardly next to a revoke action, but the description's 'unused only / used keys left alone' framing resolves that tension rather than contradicting it.

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?

Front-loaded with the action and then the eligibility rule, with the setup warning and cost note at the end. Slightly wordy in restating 'unused' twice, but every sentence carries actionable information.

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 no-parameter, irreversible-scope bulk revoke, the description covers scope, exclusions, timing caveat, and cost, and an output schema exists so return values need not be described. Nothing an agent needs before calling is missing.

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 tool takes zero parameters, so there is no parameter semantics to document and the baseline is 4. The description correctly adds no redundant parameter talk.

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 and resource ('Revoke all unused API keys') and defines the exact scope: keys never exchanged at agentAuth and never used to connect. It implicitly separates itself from the sibling revoke_agent_api_key and from list_agent_api_keys by stating 'Keys any agent has used are left alone.'

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 a clear when-not-to-use rule ('do not call this while a new agent is still setting up') and maps the action to the dashboard's 'Revoke all', which anchors the agent's mental model. It stops short of explicitly naming revoke_agent_api_key as the alternative for revoking a single known key.

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