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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds concrete consequence beyond those flags: the old key is invalidated immediately, and an uncertain outcome must not be blindly retried. It still omits blast-radius (which clients the key serves) and any auth/permission requirements.

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?

Three short sentences, each carrying a distinct fact (effect, preview mode, retry warning), with the destructive consequence front-loaded. Nothing is redundant.

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?

An output schema exists so return values need no prose, and the description covers the mutation's irreversibility, its preview affordance, and retry policy. What remains unstated is permission requirements and how the preview differs in response, both of which are relatively minor here.

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 0% and the confirmation parameter is a nested object, but the description does explain its semantics: omitting it yields a preview, including it performs the rotation. appId is left entirely to the schema, and no example payload shape is given.

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+resource ('Rotate the SDK key') and immediately scopes the effect ('immediately invalidating the old key'), which cleanly separates it from the sibling reveal_sdk_key that only reads the key. An agent can pick between them without opening either 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?

Gives an explicit operational rule: omit confirmation to get a preview, include it to actually rotate. That is real when-to-use guidance for the dry-run/commit split, though it never names a competing sibling tool as an alternative.

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