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

Goes well beyond the annotations by disclosing effects (no payment, ledger untouched), failure codes (409 not-awaiting-approval, 404 when payouts are disabled for the workspace, 403 for unclaimed sandbox workspaces), the required billing write scope, and a pointer to list_payout_runs/execution.enabled for diagnostics. For a destructiveHint=true mutation with no output schema, this is the disclosure an agent needs.

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-loaded with the action and effect, then escalating to error codes and auth prerequisites — every sentence carries non-redundant information. It is dense (four sentences of constraints) but nothing is filler; light structuring of the error/auth clauses would push it higher.

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?

No output schema exists, and the description compensates by covering the state machine (awaiting approval), error semantics, permission scope, and workspace-claim prerequisite. An agent has everything required to call it correctly or diagnose failure.

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?

Only one parameter (run_id) and the schema already documents it at 100% coverage, including the 'id on a list_payout_runs or request_payout_run result' provenance note. The description adds no format or resolution detail beyond the schema, so the baseline applies.

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 (reject) on a specific resource (payout run) plus the precondition 'awaiting approval', which cleanly separates it from approve_payout_run and retry_payout_run. The consequence clause ('nothing is paid and the ledger stays as it was') further pins down what the action means.

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 when ('a payout run that is awaiting approval') and an explicit when-not boundary ('409 when the run is not awaiting approval'), plus a self-service scenario ('The requester may reject their own request to withdraw it'). It never names the sibling alternative (approve_payout_run) it should be weighed against, so it stops short of full routing guidance.

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