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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only' repeats structured data. What the description does add beyond annotations is the matching rule (offset_ref = purchase_id) and the shape of the verdict; it does not state what happens when no matching retirement exists or how partial coverage is judged.

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?

A single dense paragraph, front-loaded with the identity and the assertion being tested, followed by the return shape. The leading 'x402-C C4 check' code is opaque filler, but the rest earns its space.

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?

Given an output schema exists, listing return fields is redundancy, but the description otherwise supplies the missing parameter semantics and the decision rule the agent needs. Only the default-required_g behavior and the no-match case are left unaddressed.

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 0%, so the description must carry the load: it does explain that purchase_id is matched against offset_ref and that required_g is the gram threshold to clear. It omits the meaningful default of required_g=0 and whether units/rounding are enforced, leaving a real gap for a 2-param tool with no schema docs.

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 (confirm/verify) and resource (a retirement of conservation credit) plus the exact quantitative condition (retires at least required_g grams). The 'offset_ref = purchase_id' mapping makes the check concrete. It does not explicitly differentiate itself from the nearby sibling verra_retirement_record, which an agent could plausibly 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?

The phrase 'the check that lets a carbon receipt's neutrality claim be honored' implies the context in which to call it, but no alternatives or exclusions are named — nothing says when to prefer this over verra_retirement_record or verify_certificate.

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