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

With no annotations at all, the description does substantial work: it discloses that this is a write to the public API, that the secret is returned exactly once, that the server retains no copy, and that the key is scoped to a single agent_id. Gaps remain around authentication requirements for the call itself and whether re-issuing invalidates prior keys.

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 short sentences, front-loaded with the endpoint and return value, followed by scope and then the storage warning. Each sentence carries distinct, decision-relevant information with no filler.

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?

No output schema exists, and the description correctly explains the return value (a key shown once, not stored server-side) along with its scope. What remains thin is caller-side preconditions such as required auth and any rate or rotation behavior, which matter for a credential-minting write.

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%, so baseline is 3; the description adds genuine meaning by explaining that agent_id determines the key's authorization scope ('can only submit checks for this agent_id') rather than just a format. label is left to the schema, which already describes it adequately.

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?

Names a specific verb and resource ('issue' implied by 'return a new API key'), pins it to the concrete endpoint POST /v1/keys, and states the key's scope ('can only submit checks for this agent_id'). None of the sibling tools (mizan_check, trust_check, search_agents) issue credentials, so the agent can distinguish it easily.

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?

Conveys implicit context via 'First request claims the name', which hints this is a one-time bootstrapping call, and explains what the credential can be used for. However, it never states when to call this versus other tools, gives no explicit 'do not call if you already have a key' exclusion, and no alternatives are named.

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