Preview Order Basket

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

Annotations declare readOnlyHint=true, and the description reinforces that orders are not placed. This aligns with the annotation. However, it adds no further behavioral context—such as whether the preview validates orders, what data it returns, or any side effects beyond being read-only. Given the annotation already covers safety, this is adequate but minimal.

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?

A single, front-loaded sentence with no redundant phrasing. It is appropriately concise, though it sacrifices depth—but conciseness itself is excellent.

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?

Despite the complexity (a basket of orders with many advanced order types and nested symbol specs), the description provides no guidance on what the preview returns, whether it validates orders, or how errors are surfaced. The output schema exists, but the agent still lacks context on the preview's purpose and behavior. This is a significant gap for a tool with this much input 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?

The only parameter is 'orders', whose schema is rich with nested OrderSpec and SymbolSpec definitions, including detailed field descriptions. The tool description adds nothing beyond the schema; it does not explain how the basket is processed or what constitutes a valid input beyond the schema. Since schema coverage is high (the nested schema is thorough), baseline 3 applies.

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 the verb (Preview), the resource (a basket of explicit orders), and the key behavior (without placing them). This distinguishes it from placement tools and from a single-order preview tool like preview_order, even without naming siblings.

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 implies usage for a batch of orders ('basket'), but does not explicitly state when to use this over preview_order or how it differs from place_order. No exclusions or alternative routing are given, leaving the agent to infer the batch use case.

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