Mint an API key (session only)

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation profile is known. The description usefully adds that the operation has no server-side dry run and is gated on confirm, but the schema's confirm field already says it returns a preview, and it never clarifies what "session only" means, whether the key secret is returned once, or that minted credentials persist until apiKeys_revoke.

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 with the action and endpoint front-loaded and zero filler. The telegraphic style ("WRITE: not executed unless confirm: true") is terse but still parses cleanly.

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 credential-minting mutation with a nested body, no output schema, and only sparse annotations, an agent still lacks critical context: what the returned key material looks like, whether it is shown once, and what "session only" constrains. Adequate as a pointer but not complete for correct, safe invocation.

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 description coverage is 67%, so the schema carries most of the load for confirm and idempotencyKey. The description adds no meaning about the nested body fields (scopes, clientId, expiresAt, guardrailIds) or least-privilege scope selection, which would be the highest-value thing a minting tool could explain.

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 ("Mint an API key") plus the concrete endpoint POST /v1/api-keys, which distinguishes it from the read/revoke siblings apiKeys_list and apiKeys_revoke. It does not name those siblings explicitly, so differentiation is inferable rather than stated.

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 confirm:true requirement and the note that nothing executes without it give usable invocation guidance. However, there is no explicit when-to-use versus alternatives (e.g., how this differs from appCredentials_set or tracking_createIngestKey for other credential types), and no prerequisites such as required scopes to mint a key.

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