Solve a captcha

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

Goes well beyond the annotations (readOnly=false, idempotent=false, openWorld=true) by disclosing wait behaviour ('up to ~50 s by default, polling automatically'), the graceful-degradation path (returns the task id), cost/billing semantics (billed to CaptchaNo, failed solves free), and token lifetime/one-use constraint ('valid for one submission and expires in about 2 minutes'). These are exactly the operational traits annotations cannot express, and they are consistent with the declared non-idempotent, non-readOnly profile.

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?

Front-loads purpose, then usage, then prerequisites, then per-type requirements, then timing/billing/pitfalls. Despite being a long description for a 12-parameter tool, every sentence carries distinct actionable content (a required-field rule, a timing limit, a billing rule, or a misuse warning) with 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 12 parameters, an output schema present, and non-idempotent semantics, the description covers the gaps that matter: per-type required inputs, wait/timeout behaviour, the fallback to get_task, billing, and token reuse limits. Return values are deferred to the output schema, so nothing an agent needs to invoke this correctly is missing.

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%, which sets a baseline of 3, but the description adds genuine cross-field conditional logic the schema cannot express per-property: which fields are required per type (recaptcha_*/turnstile → url + sitekey; datadome → url + challengeUrl + proxy; image → body). It also points to list_captcha_types for sitekey discovery, which the schema does not.

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 and resource (solve a captcha) plus the deliverable ('return the token / cookie / text needed to pass it'), and enumerates the covered captcha families (reCAPTCHA v2/v3/Enterprise, Turnstile, DataDome, image). An agent can distinguish this from get_task, get_balance and list_captcha_types without opening a schema.

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?

Gives an explicit trigger condition ('Use when an authorised browser or HTTP automation is blocked by...'), names the alternative when the call outlives its window ('call get_task with it instead of solving again'), and adds an exclusion ('Do not call repeatedly for the same captcha'). Nothing about when to use or avoid this tool is left to inference.

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