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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety bar is partly carried. The description adds genuinely non-derivable behavior: the protocol submits and pays gas, so nothing is broadcast by the agent, clarifying the mutation/commit boundary. It is silent on batch atomicity (whether a partial failure rolls back) and on the wallet-proof requirement.

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?

Two sentences, front-loaded with the cap and wallet scope, then the signing/submission step. Every clause carries information an agent needs and there is no filler.

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 20-item mutation with mandatory idempotency and wallet-proof parameters, the description says nothing about partial-failure semantics, ordering guarantees, or what the returned confidence/quantity fields imply, even though an output schema exists to cover return shape. It is adequate for invoking the tool but thin for a batch operation of this complexity.

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 83%, so the schema already documents nearly every parameter in depth, including side, amount, closePercent and targetCollateralOut. The description contributes only the batch cap and the shared-wallet constraint, adding little meaning beyond the structured fields. Baseline 3 applies when the schema does the heavy lifting.

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 a specific verb (Prepare) and resource (signable trade intents) plus two hard constraints: a cap of 20 and a shared agent wallet. That distinguishes it from the single-trade sibling problee_prepare_trade by implication, though no sibling is named explicitly.

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 lays out the full follow-on workflow: sign each signPayload.typedData and POST to /trade/execute-intent, which tells the agent this is a pre-execution step, not a broadcast. It gives no explicit when-not guidance or prerequisites (e.g. auth proof, quote freshness) and never references alternative tools by name.

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