rotate_keys

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

The description discloses the behavioral side effect: the active key is rotated, but the previous key remains valid for verification. It also notes the generated new key, which implies a mutation. Since there are no annotations, the description carries the full burden, and it does an excellent job of stating the security-relevant side effect. The only minor gap is that it doesn't explicitly mention that this changes the JWKS endpoint results, but that is implied by the context.

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 one sentence that packs all essential information: the operation, the outcome, and the use case. It is efficient and front-loaded with the action. Nothing is wasted.

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?

Given the tool has no parameters, no output schema, and no annotations, the description is nearly complete for a mutation tool. It explains the side effect and the typical use case. The only missing piece is what the response looks like (e.g., does it return the new key info?), but since there is no output schema, the description could have briefly mentioned the return value. That is a minor gap.

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 tool has zero parameters, so parameter semantics are inherently not an issue. The description doesn't need to explain parameters. A score of 4 is justified because the description effectively eliminates any need for parameter documentation, and the baseline for zero parameters is 4.

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 (rotate), the resource (signing keys), and the specific behavior (active key moves to 'previous', new key generated). It also includes a purpose ('test clients' JWKS refresh handling'), which distinguishes it from other key-related operations like get_keys_info or get_jwks.

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 implies when to use the tool: when testing clients' JWKS refresh handling. It doesn't explicitly state when not to use it or name alternative tools, but given the tool has no parameters and is specialized, the usage context is reasonably clear. However, it could mention that it's not needed for simple key inspection (get_keys_info) or general key retrieval (get_jwks).

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