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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds context annotations can't carry: the exact verification semantics, the enumerated outcome space with reasons, and the absence of auth/registration/cost. It does not discuss what happens when the receipt structure itself is malformed, but the outcome categories largely cover the failure mode.

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?

Front-loaded with the purpose and then the verification scope, then outcomes, then use cases – a sensible ordering with no filler sentences. Minor overlap between "Proof of delivery check" and "Verifies a delivery receipt", and the trailing "Free, no sign-up, no API key" is only marginally useful to an agent.

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?

An output schema exists, so return formatting needn't be explained; the nested receipt object is described in the schema. What remains for the description – what is verified, the possible verdicts, and when to reach for it – is all present and sufficient to call the 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 100%, so both parameters are already documented, including the expected W3C VC 2.0 / eddsa-jcs-2022 receipt format. The sentence about comparing a file's SHA-256 with the deliverable hash largely restates the file_sha256 schema entry rather than adding new constraints or output semantics. 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 specific verb (verifies) and resource (delivery receipt) and scopes exactly what is checked: the seller's signature over the deliverable hash and, if present, the buyer's countersignature. Its three result categories (countersigned, seller-only, invalid) and the optional file-hash comparison make it clearly distinct from the lookup and publish siblings without naming them.

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?

"Relevant to a delivery dispute or to checking a seller before payment" gives concrete situations that select this tool. It stops short of naming lookup_delivery_receipt or publish_delivery_receipt as alternatives or stating when not to use it, so it is clear context without explicit routing.

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