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

The description provides deep behavioral context beyond the annotations. It explains the complex internal routing logic (DEX router, EventTrader, CEX options) and the nature of the output (showing best CEX vs DEX per leg), which is invaluable for an agent understanding the tool's internal operations.

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 quite lengthy but highly effective. It uses clear language and front-loads the most critical information (read-only nature, routing concept) before detailing the technical implementation, ensuring every sentence is purposeful.

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?

Given the high complexity of trade routing across multiple venues (DEX/CEX/Brokerage), the description is exceptionally complete. It covers the function, the constraints, the process, the output content, and the correct next step in a workflow.

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?

While schema coverage is 75%, the description adds vital clarity to parameters like 'usdc_amount' (defining it as 'the user's own money') and specifies that 'theme' must be a 'theme/subtheme slug or label.' This aids parameter selection and context.

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 defines the tool's role as ROUTING a basket trade through execution pipelines. It specifically contrasts this planning step with the execution step, explicitly directing the agent to use 'theme_journey_trade' to place the actual order.

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 provides explicit instructions on when *not* to use the tool for execution, stating 'Nothing is placed; call theme_journey_trade to place it.' This prevents the agent from misusing the route planner as an execution tool.

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