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

Annotations only flag destructive/read/write traits. The description goes far beyond that by disclosing the non-custodial venue behavior, geo-gating of cancels, optional idempotency replay semantics, the promise that the two leg bugs never raise IDEMPOTENCY_CONFLICT, and the two-phase execution semantics. It also explains isverification enough because cancel moves no position, so no state re-read is required.

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 front-loaded with its purpose and then uses compact parameter-focused paragraphs for the nuanced fields. The content is dense and mostly justified, though the repeated 'see place_perp_order' references and the lengthy idempotency paragraph could be tightened without losing information.

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 10-para, destructive perp API with an output schema, the description covers the most safety and execution-critical behaviors: non-custodial, geo-gated cancellation, idempotency, and two-phase execution. The main gaps are practical meaning of the remaining optional parameters and the reliance on cross-references to place_perp_order for necessary details.

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%, and the description compensates for only some parameters: 'jurisdiction' (geo-gating), 'idempOTency_key' (replay rules, reuse across legs, no conflict), and 'signed_transaction'/'verify' (two-phase semantics). It leaves 'wallet_address', 'order_id', 'venue', 'ip', 'caller_id', and 'acknowledge_tier_b' without any behavioral or formatting explanation, which matters given the schema has no parameter descriptions.

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 opening line 'Cancel a resting perp order on its venue (non-custodial)' states a specific verb, resource, and scope. It clearly distinguishes cancelling a resting order from position-closing tools like close_perp_position or perp_close, and 'resting order' narrows it from order placement.

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 gives strong execution context but no explicit when-to-use/when-not guidance against alternatives such as close_perp_position, strategy_cancel, or place_perp_order. The repeated 'see place_perp_order' references explain semantics but do not tell an agent what alternatives exist or when to choose them.

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