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

Annotations cover only readOnlyHint and openWorldHint, but the description adds substantial context beyond them: the call names no route, stores nothing, charges nothing, and is rate limited to 3 a day per address. It also discloses the shape of the result (boolean plus USDC lower-bound saving plus fee), so side effects, cost, and limits are all known before invocation.

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 free/unsigned nature and the payoff, with the signed alternative last, so the agent gets the essentials first. The single paragraph is dense and mostly earns its clauses, though the saving/fee phrasing is slightly compressed enough to require a second read.

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?

There is no output schema, and the description compensates by describing the return values (route existence, lower-bound saving, Recta's cut). Combined with the rate limit, the no-store/no-charge guarantees, and the explicit next step for a signed request, an agent has everything needed to call it and act on the result.

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% and the single `body` parameter is documented as a JSON object or its JSON text, so the schema carries the type burden. The description still adds real meaning by telling the agent where the body comes from (recta_request_template) and that sender and recipient must be filled in, which the schema does not say.

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 and resource ('Unsigned trial of an evaluation') and enumerates the exact return payload: whether a cheaper provable route exists, the saving as a lower bound in USDC, and Recta's 5% of it. It is clearly distinguished from recta_prepare_signed_request and recta_send_signed_request, which the description names as the path to the actual route.

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 an explicit when/when-not split: use this unsigned call for the free estimate, and sign the same body with recta_prepare_signed_request plus recta_send_signed_request to obtain the route itself. It also points to recta_request_template as the source of the required body and states the 3-per-day-per-address ceiling, leaving no routing ambiguity against the siblings.

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