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

Annotations already mark destructiveHint=true and readOnlyHint=false, and the description reinforces this with a clear warning. It adds value by noting the key is returned only once and should be stored immediately, and that it must be passed via a specific header. This goes beyond 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?

The description is short, impactful, and front-loaded with the destructive warning. Every sentence adds value: the warning, the action, the one-time return, and the header note. No fluff.

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 destructive rotate operation, the description covers the core: what happens, the one-time return, and the header requirement. It doesn't specify the response schema (but an output schema exists) or explicitly mention that the old key becomes invalid, but that's implied by revoke. Given annotations and schema, this is adequately complete.

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% and the parameter description is self-explanatory. The tool description adds the tip about passing keys via the X-DataNexus-Key header, but this is more transport-level than parameter-level. Baseline 3 is appropriate since the schema already covers semantics.

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 clearly states the action: 'Revoke the current API key and issue a replacement.' It specifies the resource (API key) and distinguishes from siblings like generate or revoke. The verb is explicit and the outcome is unambiguous.

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 description warns it is destructive and requires human confirmation, which is crucial for safety. It implies it should be used when you need to replace an existing key, but doesn't explicitly contrast with generate or revoke. Siblings are available but not named as alternatives.

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