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

Annotations already mark readOnlyHint=true, and the description reinforces this with 'commits nothing' and 'non-custodial'. It adds useful behavioral context about returning a signature payload rather than executing anything, and clarifies the gasless nature of the operation. Minor gaps remain around output format and any prerequisites beyond having an orderId, but the core behavior is well disclosed.

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?

The description is compact and front-loaded: it immediately states the input scope and core output, then clarifies the relationship to cancel_order and when the alternative route applies. Every sentence carries useful decision-or-behavioral information, with no filler or repetition of schema details.

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 single-parameter tool with no output schema, the description gives an agent everything needed to call it correctly: what it returns, that it requires no version argument, that it commits nothing, and how it differs from cancel_order's transaction route. The ordering and signing workflow is implied clearly enough.

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?

The schema already fully documents orderId, including its source from submit_signed_order, get_order_status, or get_pending_orders. The description adds little beyond restating that the tool takes an orderId, so it does not meaningfully elevate parameter understanding beyond the required baseline.

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 clearly states a specific action—returning the EIP-712 cancellation for a given orderId—and distinguishes this tool from cancel_order by explaining that cancel_order relays the result. It also identifies the gasless/intent-order context, so an agent knows exactly what this tool produces.

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?

The description explicitly says when to use this tool: for gasless cancellation of an intent order. It also names the alternative route—cancel_order's transaction route for on-chain native-token sells—and notes that route needs no signature and no prepare. This gives clear selection criteria versus a sibling tool.

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