create_api_key

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing that the secret is returned ONLY once, that it will be visible in the AI conversation context, that the operation requires an elevated 2FA session, and how to recover from a 403. This is exactly the behavioral context an agent needs for a credential-minting write operation.

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-loads the highest-risk fact (secret returned only in this response, visible in context) before the procedural 2FA steps and the access note. Every section is distinct and earns its place given the operation's complexity.

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-creation tool with no output schema, the description supplies the critical return-value warning, the full prerequisite flow, and the authentication context. Nothing an agent needs to invoke this correctly 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?

Schema coverage is 100%, so name/scopes/environment are already documented, establishing a baseline of 3. The description adds real semantic value for profile_id by explaining the branding effect ('outbound messages sent with the key are then branded as that project'), which the schema's 'sub-account project' phrasing only hints at.

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?

Opens with a specific verb+resource ('Create a new API key') and the description clearly differentiates this from siblings like list_api_keys, revoke_api_key, and regenerate_api_key. An agent can identify exactly what this tool does 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?

Provides an explicit, numbered prerequisite flow (start_2fa with action_type 'api_key_create' → wait for user → poll get_2fa_status → call this tool) plus a documented failure path (403 means session expired, restart). It also names the authentication alternatives (PROOF_API_KEY vs start_login), leaving nothing to inference.

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