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

Annotations declare destructiveHint=true and non-idempotent, but the description goes well beyond them: anything outside Control Plane holding old values breaks, workloads only re-read secrets on restart, generated values are never visible to anyone, and database credentials from add_database retain their own password. These are exactly the consequences an agent needs before invoking a destructive rotation.

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 action and its blast radius are front-loaded, and every sentence carries workflow information rather than filler. It is dense and slightly convoluted in places ('get new random ones now, which nobody sees'), and the preview note is tacked on at the end rather than grouped with the rotation modes.

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, multi-step, two-call workflow, the description covers the full path: dry run, auto-generated rotation, user-supplied rotation, workload restart, and database special-casing. An output schema exists, so return formatting need not be repeated, and nothing material to correct invocation is missing.

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%, so the baseline is 3, but the description adds real semantics: preview is a no-op report, userSaved is only valid after a Console save, and 'No input accepts a value' clarifies that no parameter carries secret material. That last point is a meaningful constraint the schema alone does not convey.

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 states a specific verb+resource pair ('Replace a secret's values') plus its key side effect ('restart the workloads that use it'), which cleanly separates it from create_secret and the update_* family. An agent can tell what this tool does and what it is not (a plain settings update) without opening the 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?

It gives explicit conditions for the two operating paths: generated values rotate immediately, user-supplied values require a Console link and a follow-up call with userSaved: true; preview: true is defined as a no-op dry run. It never names a sibling alternative, so it falls short of a 5, but the when-to-use guidance is concrete.

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