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

Annotations declare non-readOnly and non-destructive, and the description adds real value beyond that: the relayer broadcasts and pays gas, value must equal the intent max price, and signing uses Base USDC's EIP-712 domain with the ReceiveWithAuthorization typehash pointing at the EscrowV3 address from get_intent. What it omits is failure behavior — authorization expiry handling via validBefore, nonce reuse, and what the caller observes on rejection.

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 actor, the verb, and the mechanism, then moves to the why (gasless), then the signing detail, then post-conditions. Dense but each sentence carries information; minor overlap between 'value MUST equal max price' and the schema's identical wording.

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 9-required-parameter mutation with no output schema, the description covers the role, precondition, signing construction, and downstream flow well. What remains uncovered is the return value (tx hash or funding status) and the error surface for an expired or mismatched authorization.

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 the baseline would be 3, but the description adds cross-field and formatting semantics the schema cannot: the exact EIP-712 domain, typehash, and the constraint that `to` must be the EscrowV3 address from get_intent. It adds some of this but leaves validAfter/validBefore window semantics to the schema.

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 and resource: the BUYER submits a signed EIP-3009 receiveWithAuthorization for an accepted deal's auto-minted Class-A intent. This cleanly distinguishes it from confirm_funding, create_intent, and accept_deal with no ambiguity about who calls it or what it produces.

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?

Explicitly frames the condition (deal already accepted, buyer role) and contrasts with the on-chain alternative of approve + createIntent that requires ETH for gas. It also names the sequencing after the seller's reveal. It does not name sibling tools directly, so it stops short of the top band.

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