request_approval

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

Annotations already indicate side effects (readOnlyHint=false, destructiveHint=true). The description adds valuable behavior: the grant is server-authoritative, the returned approval_id is single-use and bound to the plan's current validation digest, and operator identity can only be injected by a trusted host. No contradiction with 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 three sentences with no filler. It front-loads the core purpose, then appends auth/compatibility context and return-value behavior, all of which earn their place.

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?

This is a side-effectful approval tool in a broad sibling set, so an agent would benefit from more explicit routing versus validate_plan or execute_plan, and from more detail on the optional digest parameters. The output-schema presence reduces the need to explain return shape, and the single-use approval_id behavior is already covered.

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%, so the description carries a heavier burden. It explains operator_token's special purpose and clarifies validation_digest's binding relationship, but plan_id, bundle_digest, and recurrence_digest are left mostly to inference from their names. Partial compensation, not complete.

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 action: issuing a server-authoritative approval grant for a plan requiring confirmation. This clearly distinguishes it from sibling tools like validate_plan or execute_plan, since the focus is on approval rather than validation or execution.

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 identifies when the tool applies ('for a plan requiring confirmation') and gives concrete usage guidance around operator_token, noting it is only for local/dev compatibility and that callers should never supply the recorded operator identity. It does not explicitly name alternatives, but the intended context is clear.

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