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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds real value on top: it enumerates what is checked (signature, status, expiry, per-payment cap, remaining budget, payee list), discloses the result shape (allow/deny with reasons plus a signed attestation), and states there is no auth requirement ('Free; no key needed'). It is slightly weaker on latency/determinism, but the auth and return-format disclosures go well beyond the 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?

Two sentences, front-loaded with the audience and the decision being made, with zero filler. Every clause (verification targets, return shape, no-key/no-cost) carries information an agent needs.

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 usefully describes the return (allow/deny with reasons and an attestation), and it covers auth and cost. It leaves the exact response structure and any error/deny reason taxonomy unspecified, which is a minor gap for a 3-param verification tool.

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 payee, mandate_id and amount_usdc are already documented in the schema. The description contextualizes them (a presented mandate ID, a payment amount, the cap/budget it must fit within) but adds no new format or constraint detail beyond the schema. Baseline 3 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 precise verb (verify/check) and resource (an agent's payment mandate) and frames it as a yes/no authorization question directly from the payee's point of view. It clearly distinguishes itself from siblings like mandate_get (fetch), mandate_create, mandate_revoke and mandate_spend, which do not perform verification.

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?

Named audience ('merchants, payment facilitators and counterparties') plus the triggering question ('did a human authorize this AI agent to pay you this amount?') tells the agent exactly when to reach for it. It stops short of naming when NOT to use it or pointing to mandate_get for raw mandate data.

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