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

Annotations already indicate idempotent and non-destructive, but the description adds meaningful behavioral context: it is a self-report that does not prove profitability or accuracy, and it enforces data hygiene (no wallet data, keys, prompts, etc.). This goes beyond the annotations and gives the agent a clear mental model of the tool's side effects and limitations.

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 concise—four sentences—and each sentence serves a purpose: main action, when to call, submission constraints, and purpose/limits. It front-loads the core purpose and immediately gives practical usage instructions without fluff or repetition.

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 self-reporting tool with no output schema, the description covers the necessary context: why to call, when, what to submit, and what the report does and does not prove. With annotations covering idempotency and non-destructiveness, the description is sufficiently complete for an agent to invoke it correctly, though it omits details about possible response codes or error handling.

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 schema description coverage is low (20%), so the description must compensate. It references 'bounded enums' and 'one-time token', which map to the enum parameters and outcome_token, and instructs to avoid extraneous data. However, it does not explain the meaning of each parameter (e.g., what 'execution_result' values represent) beyond their names. It provides partial semantic guidance but not enough to fully replace schema descriptions.

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 precise action ('Close the behavioral feedback loop') and a specific resource ('one prior evaluate_prediction_market receipt'), and lists concrete scenarios that trigger the call. It clearly differentiates this from siblings like report_tool_outcome by focusing exclusively on prediction-market preflight outcomes, leaving no ambiguity about what the tool does.

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 explicitly states when to call the tool: after the listed behavioral actions (proceeds, reduces position, etc.) or on execution failure. It also specifies what to submit (bounded enums and one-time token) and what to never include. While it doesn't name alternative tools or say 'use this instead of X', the scoping to prediction-market preflight implicitly excludes broader reporting tools, providing adequate usage guidance.

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