Api keys: create

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

Rich disclosure beyond the annotations: the raw key is shown once and never retrievable, expiry is 1–365 days (90 default), permissions the caller lacks are silently dropped with a warning, and the key lands only in the output or a CLI profile. These are the exact behavioral facts an agent needs and none are in 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?

Front-loaded with the core action and generally tight. The 'shown once and never retrievable' / 'appears only in this output... store it at once' pairing is mildly redundant, and the trailing 'Returns JSON' adds little, but the paragraph earns its space overall.

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?

With no output schema, the description carries return information and does so adequately, emphasizing that the raw key is delivered once in the output. Annotations cover the safety profile (non-readOnly, non-destructive). Minor gap: it doesn't describe the JSON shape returned, but the critical one-time-secret caveat is covered.

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% (baseline 3), and the description adds meaning on top: save_as diverts the raw key into a CLI profile, expires_in semantics/range, and that requested permissions fall back to what the caller actually holds. Slightly exceeds what the schema alone conveys.

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 (Create) and resource (API key / project API key) with concrete scope details: permissions, expiry, and where the raw key goes. An agent can distinguish this from api_keys_list and api_keys_revoke without opening the schema.

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?

Usage is largely implied by the create verb rather than stated. It hints at the save_as alternative ('goes straight into a CLI profile with save_as') and points to `fetch` on /permissions for valid names, but gives no explicit when-to-use/when-not guidance or comparison to sibling tools.

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