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

Beyond the annotations, the description discloses non-custodial execution, an unsigned base64 tx to sign and broadcast, x402 payment_header requirements past the free tier, separate collateral deposit/withdraw needs for leverage/collateral changes, jurisdiction geo-gating, and idempotency_key replay semantics. This is rich, relevant behavioral context that annotations alone do not provide.

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 the core action and then uses compact paragraphs for payment, jurisdiction, and idempotency details. Every sentence adds functional value; there is no filler or redundant restatement.

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 12-parameter tool with no output schema details shown, the description covers the most critical behavioral aspects: return format, payment requirements, jurisdiction limitations, collateral behavior, and retry semantics. Minor gaps remain around unexplained parameters like pay_in_crank, caller_id, and ip, but the overall context is sufficient for an agent to invoke the tool correctly in most cases.

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?

With 0% schema description coverage, the description compensates by explaining key parameters: new_tp/new_sl as TP/SL triggers, new_leverage and add_collateral as requiring separate collateral handling, jurisdiction geo-gating, and idempotency_key for replay behavior. However, not all 12 parameters are covered — pay_in_crank, caller_id, and ip are left without explanation.

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 opens with 'Modify an existing open Drift ORDER by order_id (non-custodial)', giving a specific verb, resource, and scope. It clearly distinguishes this from siblings like cancel_perp_order, close_perp_position, and perp_open_long by targeting existing open orders and TP/SL adjustments.

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 states when to use the tool: to modify an existing open Drift order by order_id, with prerequisites like the order being open and non-custodial. It also flags geo-gating for jurisdiction changes and points to perp_open_long, but it does not explicitly enumerate alternatives or exclusions such as cancel/close.

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