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

Goes well past the annotations: discloses that the old value is irrecoverably gone, that already-running workloads keep the stale value until restart, that non-GitOps clusters get an immediate re-apply, and that secrets.manage (owner/admin) is required. These are exactly the operational consequences an agent needs beyond destructiveHint=true and idempotentHint=false.

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?

Front-loads verb and resource, then layers consequences, permissions and the exclusion clause in a logical order. It is dense but nearly every sentence carries a distinct fact; the parenthetical about non-GitOps clusters is the one spot that reads as an aside.

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, non-idempotent mutation with no output schema, the description covers irreversibility, propagation timing, running-workload behavior, required permissions and the scope boundary. An agent has everything needed to call it correctly and warn the user.

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%, with name, length and prefix all documented including the sentinel form for name, so the baseline is 3. The description only adds that no value is ever supplied, which explains the absence of a value parameter but adds little to the documented parameters themselves.

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?

Names a precise verb and resource ('Rotate an organisation secret') and immediately explains the mechanism: a new value is generated and replaced in place, sentinel unchanged. The closing clause 'It never takes a value: a secret the person must type is replaced on the secrets page' implicitly separates it from user-input secret flows such as request_secret.

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 clear context for when this applies (in-place rotation, resources pick up the new value on reconcile) and one implicit exclusion (person-typed secrets belong on the secrets page, not here). It does not explicitly name sibling alternatives like create_secret or request_secret, so routing relies on inference.

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