report_captcha

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

Discloses a real behavioral trait beyond the annotations: outcomes order the strategies tried next time on that route, so the effect is persistent and feedback-driven. Annotations only say readOnlyHint=false. It could note idempotency or overwrite behavior, but the feedback-loop effect is the key non-obvious trait and is covered.

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?

One dense sentence states the action, the payload, the key, and the reason to call it. No filler, and the routing instruction is front-loaded.

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?

Complete enough for a small 3-param mutation tool with no output schema: action, post-condition, and the consequence of omission are all present. It stops short of 5 only because return behavior and error handling are not mentioned.

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 description coverage is 100%, so the schema already documents good, note, and taskId fully. The description adds only the good semantics, which the schema also states. Baseline 3 is correct when the schema does the work.

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 (report) and resource (captcha outcome), with the boolean semantics spelled out (good=true worked, good=false rejected) keyed by taskId. The relationship to the solve_* family is explicit, distinguishing it from the solve tools.

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?

Explicitly says when to call it: after submitting a token from solve_turnstile, solve_recaptcha_v2, or solve_hcaptcha. Also gives the when-not consequence: an unreported rejection is repeated because it feeds strategy ordering, which is a strong reason to always report.

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