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

Annotations only mark readOnlyHint false and destructiveHint false, so the description carries the full disclosure burden. It provides rich behavioral detail: secret format (er_live_/er_test_), one-time plaintext return, non-retrievability, permission requirements (Editor+owner), and policy dependency. This aligns with the annotations while adding significant value beyond them.

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?

Four dense sentences deliver the core purpose, key behaviors, permissions, and policy reference without redundancy. Each sentence contributes distinct information and the structure is front-loaded with the main action.

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?

The description covers purpose, usage boundaries, return behavior (plaintext exactly once), permissions, and policy linkage. Since there is no output schema, the one-time return note adequately explains what to expect. It also references the related policy tool for additional context, making this comprehensive for the tool's complexity.

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 schema covers 100% of parameters with descriptions, including the mode enum and null semantics for ttlDays. The description adds contextual background about the secret prefix and permissions, but does not need to repeat parameter details. This matches the baseline of 3 for full schema coverage.

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?

The description opens with the specific verb 'Mint' and resource 'inbound relay (data-plane) API key', clearly identifying the tool's function. It explicitly distinguishes this from management keys by noting the secret cannot call management MCP or REST, separating it from sibling tools like create_project_token.

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?

It states the use case — 'for callers to send traffic to this project' — and sets boundaries by noting the key cannot call management APIs. It also references get_key_policy for policy constraints, but does not explicitly name an alternative tool for creating management keys. This is clear context with implicit exclusions, though not a fully explicit when-to-use comparison.

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