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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with concrete behavior: it holds no key and calls nothing, so the agent knows this is pure local computation with no network effect or secret exposure. It stops short of describing error cases (e.g. malformed body, address mismatch) or exactly what the returned header set contains, which keeps it off a 5.

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?

Three sentences, tightly packed and front-loaded with the core verb before the follow-up call and the suggested entry point. Nearly every clause earns its place; the only minor cost is the trailing issued_at reference that adds ambiguity rather than instruction.

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 naming both return artifacts (the exact message to sign and the headers to send). Combined with the explicit hand-off to recta_send_signed_request and the pointer to recta_service_descriptor for request bodies, an agent has everything needed to call this 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 75%, so the schema carries most definitions, but the description adds real cross-field meaning: the body's "sender" must equal the signing address, and idempotency_key is mandatory for the primary POST route. The only blemish is that it references an issued_at value that does not appear as a parameter in the input schema, which could momentarily confuse an agent about whether it must supply one.

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 artifact: computes the exact message an EVM wallet must sign (EIP-191 personal_sign) for one Recta request, plus the headers to send. It also distinguishes itself from the sibling it hands off to (recta_send_signed_request), so an agent can separate the two without inspecting either schema.

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 explicit sequencing: call this first, then call recta_send_signed_request with the same method, path, idempotency_key, body and issued_at plus the signature. It also names the recommended starting route (POST /v1/golden-corridor/commercial-evaluations) and points to recta_service_descriptor for the body shape.

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