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

Beyond the annotations (readOnly, idempotent, non-destructive, openWorld), it discloses the key constraint that only unsigned bytes are produced and that signing must happen elsewhere, plus the rate limit (10 calls/day) and the paid fallback paths via x402 or X-API-Key. It does not describe behavior on an invalid signature or unsupported type, which is the main remaining gap.

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, front-loaded with the core purpose, then the safety constraint, then pricing. No sentence is redundant, and the server attribution is a minor, harmless tail.

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 two-parameter encoder with an output schema, full param coverage, and annotation-backed safety profile, the description covers purpose, constraints, and cost. The one thing an agent might still need is guidance on complex argument typing, but overall it is complete enough to call 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 100% and both parameters already carry descriptions and examples, so the schema does the heavy lifting. The description only restates that inputs are a signature and encoded args; it adds no extra detail such as how to express nested tuples or arrays within the args string. Baseline 3 applies.

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 description states a specific verb and resource: build calldata from a function signature and arguments, and clarifies the output is selector + encoded args. That is concrete enough to distinguish it from calldata_decode. It stops short of naming that sibling or explicitly stating it is the inverse operation, so it falls just below the top mark.

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?

It gives a clear usage context: offline/unsigned calldata preparation for a human or wallet to review, which rules out signing. There are no explicit exclusions or named alternatives (e.g., use calldata_decode to reverse-engineer), so there is room for more routing guidance.

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