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

With annotations already declaring non-readonly/destructive/openWorld, the description still adds substantial behavioral context: mandate verification via AP2 gateway, payer-signed EIP-712 escrow release, payment only to the immutable worker, signed receipts, and hard constraints (no private keys, no payee/payer substitution). It also discloses cost, auth header binding, and the 25.00 USDC cap.

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?

Dense but front-loaded: the authorization rule and verification model come first, then endpoint/pricing, then state and dispute behavior. Given the tool's complexity each sentence carries information, though the mid-section mixes pricing and auth details and could be tighter.

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, high-risk payment tool with no output schema and 40% param coverage, the description covers authorization, verification, settlement, fees, state machine, dispute/refund branches, and security prohibitions. It omits return-value shape and per-parameter detail, but partially compensates by pointing to /api/workorder-contract.

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 only 40%, so the schema does not carry the full burden. The description explains the semantics of the mandate fields (unexpired, unused, holder-bound, exact order intent) and the wallet-proof binding, but says nothing about idempotency_key, presentation, or challenge_token, deferring all schema detail to the external /api/workorder-contract doc.

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 (release/approve) and resource (delivered order) and immediately scopes it: 'Only the hirer may approve a delivered order.' The sibling set (accept, deliver, fund, dispute) is implicitly differentiated via the state machine and dispute/refund branches, so an agent can place it correctly.

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 a clear precondition ('delivered order', hirer-only) and an exclusion path ('Disputed orders freeze release and retain an expiry refund path; expired funded orders refund only the hirer'). It does not name sibling tools by name as alternatives, which is the only gap.

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