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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the remaining burden is cost/auth, which the description discloses: '$0.03 USDC via x402.' That is genuinely useful behavioral information absent from structured fields. It does not, however, describe latency, rate limits, or failure modes.

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 tight sentences, no filler; the exclusion list and price are front-loaded after the scoping clause. The opening sentence is a grammatical fragment that requires parsing, which slightly blunts an otherwise efficient structure.

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?

An output schema exists, so return-format explanation is unnecessary; the description focuses on selection context, exclusions, cost, and fallback routing, which is the right allocation of space. The one real gap is the unexplained parameter set, which is the schema's fault as much as the description's.

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 0% across six parameters, five of them required, so the description must carry the load and largely does not — sellToken, buyToken, sellTokenDecimals, buyTokenDecimals and routingId are never explained. Only indirect hints exist ('exact-in' implies amount semantics, 'size sensitivity' implies amount matters), which is well below what a 0%-coverage six-param schema demands.

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 names the resource and scenario precisely: 'quote-derived execution conditions, network cost, and size sensitivity' for an 'exact-in ERC-20 swap on Base,' which is unmistakably distinct from siblings like signal_layer_catalog or structured_extract. It stops short of a clean verb+object statement (it reads as a usage condition rather than 'returns X for Y'), so an agent infers the output rather than being told it.

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?

Explicit when-to-use ('before an exact-in ERC-20 swap on Base when ... matter') and an explicit when-not list ('generic historical prices, personalized investment advice, or a signed transaction'). It also names the alternative to consult when unsure (signal_layer_router first, for free), which is exactly the routing guidance an agent needs.

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