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

Annotations mark this as non-readonly, non-idempotent, and non-destructive; the description adds useful context beyond that by disclosing the no-auth requirement and the asynchronous polling workflow. It does not warn that resubmitting the same claim creates a separate submission, which matters given idempotentHint=false.

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 sentence that front-loads the auth benefit and the core action, then ends with the polling instruction. No filler.

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?

With an output schema present, the return values need no explanation, and the description covers purpose, auth, and the polling follow-up. Only the non-idempotent resubmission behavior is left implicit.

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 100% with a single well-described parameter ('one statement you believe, 15-1200 chars'). The description adds only the mild nuance that the input may be a question or a claim, so it does not meaningfully extend the schema.

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 and resource ('send one question or claim') and names what the engine returns ('one conclusion'). It also distinguishes itself from the sibling try_result by assigning polling to that tool.

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 gives clear context ('No account needed') and explicitly routes the agent to try_result for polling, which is the key follow-up action. It does not, however, state when to prefer this over other submission tools like critique or vote.

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