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

Annotations already cover readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower; the description still adds meaningful context beyond them — that inputs must be public and non-personal, that no account is required, and that the output is 'a compilation, not certification or advice'. It does not mention pagination or the 200-item cap behavior, which are left to the schema.

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?

Four short sentences, each doing distinct work: trigger, key input, return shape, and caveats. The use case is front-loaded and there is no filler or redundancy.

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 enumerating the returned record families plus Merkle proofs and gaps. Combined with 100% schema coverage for the three nested parameters, an agent has everything needed to call this correctly without further documentation.

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 100%, so the schema already documents `subject`, `scope` and `requester` in detail; baseline 3 applies. The description echoes the subject form (public id or https URL) and adds the privacy constraint ('inputs must be public and non-personal'), but adds nothing about scope/categories/receipt_ids semantics beyond the schema.

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 ('Build an evidence pack') and enumerates the returned record types (conformance, watch, witness, repair, incident, gaps), which is far more than a restatement of the title. It distinguishes itself from narrower siblings like gaip_incident_bundle by framing the result as a broad compilation, though it does not name any sibling explicitly.

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 triggering situation: 'Use this when an insurer, auditor or buyer asks what evidence exists about an agent or supplier.' The `requester.purpose` enum (INSURER, AUDITOR, BUYER) reinforces that framing. It does not, however, say when to prefer a narrower sibling such as verify_gaip_receipt or inspect_counterparty_evidence instead.

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