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

Annotations only supply title and destructiveHint=true, so the description carries most of the burden. It does so well by disclosing the critical irreversible trait: the plaintext key is returned once and cannot be retrieved later unless recoverable is enabled. It still omits auth/permission requirements and prefix or expiry consequences, keeping it short of a 5.

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 sentences with no filler, and the one-time-return warning is front-loaded immediately after the purpose. The trailing endpoint reference is compact and costs little.

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?

There is no output schema, so the description correctly compensates by describing what the response contains (the plaintext key, shown once). With all 11 parameters documented in the schema and destructiveHint declared, the agent has what it needs, though permission requirements and default behaviors aren't restated.

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 100%, so the baseline is 3, but the description adds genuine meaning for the recoverable flag by tying it to key retrievability, a consequence not stated in the schema. This lifts it above baseline, though the other ten parameters get no added interpretation.

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 ('Issue a new API key under an API') and names the parent resource, which separates it from siblings like unkey_create_api and unkey_create_identity. An agent can identify the operation without opening a 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 implied by the operation itself (issuing a key), and the description adds the conditional 'unless recoverable is set', but it never states when to choose this over unkey_create_api or unkey_update_key. No exclusions or prerequisites are given beyond the single-return warning.

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