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

With no annotations, the description carries full burden and does an excellent job. It discloses side effects ('Signs nothing and moves nothing'), error handling ('Plans nothing it cannot execute... comes back in unsupported with a reason'), and output expectations ('Every leg reports executable'). It also explains how dependencies are built (third leg depends on second, amount from actual delivery). This is comprehensive and directly address what an agent needs to know.

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 lengthy but every sentence adds value: it front-loads the core purpose, gives a concrete example, explains dependency handling, and states limitations. It could be tightened, but it is well structured and not redundant, earning a 4 rather than a 3.

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 no annotations and no output schema, the description is thorough. It explains the type of request, dependent leg construction, cross-chain support, unsupported cases, and output fields (executable). While it doesn't provide a full response schema, it gives enough for an agent to call it correctly and interpret the result, which is strong for a complex tool.

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 coverage is 50% (only message is described in the schema, with 'The user's request, verbatim. Do not pre-parse it.'). The description adds context about what the message should contain (DeFi request) and gives examples, but it does not add anything about userId, which remains unexplained in both the schema and description. Thus the description compensates for message but not for the undocumented parameter, landing at a baseline 3.

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?

States a specific verb+resource: 'Turn ONE natural-language DeFi request into the dependent actions it actually contains.' The description immediately distinguishes it from execution tools by noting it 'Signs nothing and moves nothing,' and the examples clarify the cross-chain dependency modeling. It is clearly differentiated from siblings like ava_lend_execute or ava_approve_execute.

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?

Explains when to use it: for breaking a single complex request into dependent executable steps, including cross-chain. It implies it is the planning step before execution, and explicitly states it does not sign or move funds, which signals it is not for execution. However, it does not explicitly name alternatives (e.g., ava_plan_standing) or state conditions for when not to use it, so it stops short of a 5.

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