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

Annotations already cover read-only, idempotent, non-destructive safety. The description adds substantial context beyond them: transient processing with no storage/logging/retention, server-vs-browser compute delegation and the returned delegation URL, gpu delegation behavior, and offline receipt verification via the FV-status snapshot. These are genuine behavioral traits, though the framing is boilerplate-heavy rather than operational detail.

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 purpose line is front-loaded, but the block is long and mixes useful facts (retention, compute binding, provenance chain) with marketing-style boilerplate ('Deterministic OpenChainGraph compute node', URLs, FV-status hash). Several clauses repeat the compute-mode semantics already in the schema, diluting density.

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?

For a complex, nested-schema tool with an output schema and full annotations, the description supplies pipeline context, compute/delegation behavior, and a privacy constraint. Return-value details are unnecessary given the output schema, and the remaining gap is only explicit sibling disambiguation.

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 compute, parent_hashes, parent_tool_ids, and policy_parameters; the baseline is 3. The description adds only marginal semantics (that parent_hashes sets chain.parent_hashes in the export) and explicitly defers policy_parameters fields to the manifest, so it does not meaningfully exceed structured data.

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 opening states a specific verb and resource ('AP2 PaymentReceipt Verifier'), and the body clarifies it is an OpenChainGraph attestation_mandate compute node that exports an AP2 artifact with execution_hash. It gives pipeline position ('Output feeds: art-01-ap2-mandate-chain-validator...'), but never explicitly distinguishes itself from close siblings like validate_ap2_mandate_chain, verify_execution_hash, or build_ap2_cartmandate_hashchain, so an agent must infer the boundary.

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?

There is real operational guidance ('Use synthetic or anonymised inputs only', compute modes, gpu:true always delegates), which implies when to invoke it. But there is no explicit when-to-use/when-not or named alternative among the many AP2 verifier/validator siblings, leaving routing to inference.

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