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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds substantial context beyond them: expiry semantics ('once its release-by date passed undecided'), signed and chained decision records, an authentication requirement ('Needs the organisation's key'), and the demo-item exception (aprd_) where no key is needed.

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 status outcomes are front-loaded in the first sentence, and the safety rule and auth note follow logically. It is dense and slightly run-on, but nearly every clause carries distinct information an agent needs, with no filler.

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?

With no output schema, the description still conveys the return shape: the status value, an agent_approval { id, role } on approval, and the approver's reason on rejection. Combined with the auth requirement and the release prohibition, an agent has everything needed to call and act on this tool correctly.

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 already 100%, so the apr_/aprd_ format and provenance (POST /api/v1/agent/run with policy_id) are documented in the schema. The description adds meaning beyond that by explaining the operational consequence of the aprd_ prefix — demo items do not require the organisation's key — which the schema never states.

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 and resource ('Read a payout ... by approval_id') and enumerates the four outcomes (awaiting_approval, approved, rejected, expired). This clearly separates it from sibling tools like release_status, request_payment_approval, and record_release, which an agent could otherwise confuse it with.

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 explicit when-to-use context plus a hard exclusion: 'Do not release a payout while it is awaiting approval, rejected or expired.' It also routes the agent forward by naming record_release as the consumer of the returned agent_approval object, so the next step is unambiguous.

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