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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the status vocabulary (prepared, needs_attention with reasons, no_evidence), the rule that missing assessment/approval/release records surface as 'no evidence' in the export, and the auth requirement (pr_sample needs no key; a real run needs the router key that made it).

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 opening sentence sets the lifecycle scope up front and the second sentence delivers the per-payment payload and the export variant. It is dense and mostly waste-free, though the two clauses about what is read and what the export shows overlap slightly.

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 carries the burden of describing the return shape, and it does so at a useful level of detail (statuses, assessment, Rate Receipts, approval, release record, landed outcome, and export semantics). What is missing is minor — no mention of pagination, ordering, or error behavior for an unknown run_id.

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 all three parameters are already documented in structured fields, which sets the baseline at 3. The description adds marginal meaning — that run_id comes from run_payments or pr_sample and that export returns the audit export — but largely restates what the schema says.

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 uses a specific verb ('Reads the run by run_id') and enumerates what is returned per payment: status, assessment, Rate Receipts, approval, release record, and what landed. It also distinguishes the export mode from the normal read. It stops short of naming which sibling to use for other status needs (e.g. release_status, approval_status), so differentiation is only implicit via the 'run_payments' reference.

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?

Usage is implied rather than stated: the reader infers that export: true is for audit purposes and that pr_sample is for keyless trial. There is no explicit when-to-use versus approval_status, release_status, or track_payment_settlement, and no stated exclusions.

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