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

Adds substantial context beyond the annotations: the exact 0.25% fee, the recipient address, the router address, the refusal conditions, and the explicit 'holds no keys; nothing is sent' assurance. The readOnlyHint is consistent with a builder that returns an unsigned payload and never broadcasts.

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 purpose, then constraints, in a compact paragraph with no filler. The raw hex addresses are dense but earn their place as verification data for an agent building calldata.

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 5-parameter unsigned-transaction builder with an output schema, the description covers purpose, pricing, refusal guards, and key-handling. It could state whether the returned calldata is chain-specific or note rate-limit behavior, but nothing essential to correct invocation is missing.

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 description coverage is 100%, so the schema already documents side, token, amount, wallet, and slippage semantics. The description adds no parameter-level detail beyond what the schema provides (default side=buy, 18-decimal amount, 42-char addresses are all in the schema), so the 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?

States a specific verb+resource: builds the UNSIGNED KyberSwap transaction to swap a graduated pons token on Robinhood Chain. It distinguishes itself from the read-only curve/card siblings by making clear it produces a transaction payload, not data about a token.

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 says when it is refused (verdict 'avoid' or quote older than 30s) and points to rhc_curve_card for a live curve check. It stops short of contrasting itself with the near-identically-named sibling swap_build_checked, so the agent still has to infer that routing.

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