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

With no annotations, the description carries full responsibility for behavioral disclosure. It clearly states that the tool returns an unsigned envelope, that authorization only occurs after user signature, and that missing bounds are returned in 'missing' and block signing. It also explains the minGainBps requirement to prevent the agent from choosing financial thresholds. These are meaningful, non-obvious behaviors fully disclosed.

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 long (around 200 words) but every sentence adds value: it explains the concept, contrasts with a sibling, lists the bounds, explains the missing-field behavior, and justifies minGainBps. It is front-loaded with the core purpose, and while verbose, it is efficiently organized without redundancy.

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?

The description covers all critical aspects for correct invocation: what it does, when to use it (vs. workflow), what inputs are expected (message content), what happens with missing info, and the authorization flow. It also explains a non-obvious parameter requirement. No crucial information seems absent for an agent to correctly call this 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 67%, leaving one parameter without a description (userId). The description adds critical context for minGainBps ('required from you because users say the best yield rather than a basis-point floor') and interprets the 'message' parameter as containing the cadence and bounds. It does not explain userId further, but that parameter's purpose is self-evident from its name. The description compensates for the coverage gap by providing richer semantic context for the key parameters.

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 states a specific verb ('turn a request for REPEATED autonomous action into an envelope of bounds'), names the resource (an envelope of bounds), and explicitly contrasts with ava_plan_workflow. It clearly differentiates from sibling tools by focusing on cadence-driven actions.

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 explicitly says 'Use this instead of ava_plan_workflow when the request describes a cadence,' providing a direct alternative and selection condition. It also explains the underlying rationale (approving each rotation defeats the point), leaving no ambiguity about when to pick this tool.

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