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

The description adds substantial behavior beyond the annotations: challenges expire quickly, an expired challenge produces a bare 'verification failed' indistinguishable from a wrong answer, and challenge_url causes CapSkip to fetch the endpoint while challenge_json is solved locally. It also characterizes the solve as deterministic and fast, which is exactly the operational context an agent needs.

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 definition is front-loaded with the core purpose, then states the two input modes, the return-value placement, and a targeted expiration warning. Every sentence earns its place; the important operational warning is placed clearly and does not bloat the text.

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?

Combined with a 100%-covered input schema and an output schema, the description covers the full workflow: what to read, which inputs to supply, what to do with the token, and the critical failure mode. Nothing needed to invoke the tool 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?

The input schema already documents all five parameters with descriptions, and the description mostly restates the challenge_url/challenge_json choice that the schema already explains. It adds workflow-level color (fetch versus local solve) but no new constraints or formats beyond the schema, so the schema-coverage baseline of 3 is appropriate.

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 opens with 'Solve an ALTCHA proof-of-work challenge', naming a specific verb, resource, and task. It differentiates the tool from recognition-based captcha solvers by explicitly stating there is nothing to read and that the solve is deterministic, so an agent can distinguish it from sibling captcha 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?

It gives clear when-to-use context: for an ALTCHA challenge, pass either challenge_url or challenge_json, with the trade-off that challenge_json is solved locally with no network request. It does not explicitly name sibling tools or state when not to use this tool, but the proof-of-work vs recognition contrast plus the two alternative inputs make the intended use clear.

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

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

The description discloses key behaviors beyond annotations: token is verified server-side and any edit invalidates it, URL mismatches cause permanent refusals (not intermittent), and the result carries a User-Agent that must be used for submission. These are critical operational traits not present in the schema or annotations, enriching the agent's understanding of side effects and constraints.

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 a single paragraph but well-structured with an 'IMPORTANT' callout for the URL requirement. Every sentence contributes actionable information—challenge behavior, token handling, and troubleshooting. It is slightly long but not padded; the density justifies the length.

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 captcha-solving tool with two required parameters, an output schema, and a nested proxy object, the description covers the essential operational details: token usage, server-side verification, URL accuracy, and User-Agent alignment. It does not detail proxy behavior beyond the schema, but given that the schema already documents proxy semantics, the description is complete enough for an agent to solve correctly.

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 rich per-parameter descriptions, so the baseline is 3. The description adds extra context for the 'url' parameter (must be the actual page, mismatch is permanent) and introduces the User-Agent alignment that affects how 'proxy' and 'url' are used. This goes beyond schema, providing meaningful semantic guidance.

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: 'Solve a CaptchaFox challenge.' It further specifies the nature of the challenge (browser scoring, often no puzzle) and the output format (token for 'cf-captcha-response'). This clearly distinguishes it from other captcha-solving siblings by naming the provider and the token's placement.

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 gives explicit operational guidance: the URL must be the exact widget page, the User-Agent must match the one used at solve time, and errors are often due to URL mismatch rather than key failure. It does not explicitly compare with alternatives (e.g., 'use ReCaptcha tool for other providers'), but the tool name and context make the target provider obvious, so the guidance is sufficient for selection.

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

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

The description goes well beyond the annotations, disclosing that the answer must be submitted verbatim, that trimming or re-encoding invalidates it, that the challenge key is single-use and short-lived, and that CapSkip deliberately holds the result for about two seconds to avoid fast-solve rejection. This is rich behavioral context that annotations alone do not provide.

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 appropriately sized for an unusually complex captcha solver. It front-loads the core purpose, then explains the non-standard answer formatituation, verbatim requirement, and timing behavior in compact sentences. Each sentence carries necessary information without 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?

Given the 100% schema coverage, existing output schema, and detailed annotations, the description covers all the unique behavioral requirements an agent must know to invoke and consume the result correctly. Nothing essential 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%, so the baseline is 3. The tool description does not add parameter-level meaning beyond the schema, but it does not need to because every parameter already has a detailed schema description. No contradiction or missing compensation is present.

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 names a specific verb and resource: 'Solve a Capy Puzzle captcha' and explains what kind of puzzle it is. It also distinguishes the tool from siblings by explicitly stating that, unlike every other captcha tool here, the answer is not a single token.

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 gives clear context for when to use this tool: when dealing with a Capy Puzzle captcha, and contrasts it with 'every other captcha tool here' by explaining the three-value answer. It does not explicitly list when not to use it or mention sibling tools by name, but the unique answer format and field names provide strong usage direction.

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

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

Annotations only declare readOnly=false, openWorld=true, and destructive=false, so the description carries the burden of behavioral disclosure. It adds substantial context: nothing is shown on screen, two unrelated protocols share the name and sitekey namespace, a wrong solution returns a well-formed but rejected token with no diagnostic, the form field differs by version, and solve time is not constant. This goes far beyond the structured annotations.

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 information-dense with no filler. It front-loads the core purpose, then adds the critical protocol warning, version-selection guidance, field-name differences, and latency caveat in a logical order. Every sentence earns its place.

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?

Given the 8-parameter complexity, nested proxy object, enums, and output schema, the description plus schema together cover protocol selection, failure modes, version-specific form fields, and variable solve time. There is no critical missing context for an agent to invoke this tool correctly.

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 rich parameter descriptions, so a baseline of 3 applies. The description adds extra operational meaning beyond the schema by explaining how to choose between version and module_script, why sitekey alone is not a reliable version signal, and which form field names correspond to each version.

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 begins with a specific verb, resource, and type: 'Solve a Friendly Captcha proof-of-work challenge.' It also clarifies the unusual v1/v2 protocol split, which distinguishes this tool from the sibling captcha solvers without relying on the 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?

It explicitly tells the agent to send version or module_script, warns that solving the wrong protocol produces a token the site rejects, and notes that difficulty varies per request. It does not name sibling alternatives for exclusion, but the captcha-family context and protocol-specific guidance are strong enough to guide correct invocation.

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

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

No contradiction with annotations (readOnlyHint=false, destructiveHint=false). Description adds valuable behavioral context beyond annotations, such as single-use challenge expiry, the need for immediate fetching, and that results should be posted back like the site's own front-end. This enhances transparency about failure modes and usage constraints.

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?

Description is three sentences, front-loaded with the core action and return values. It includes an important usage warning without unnecessary elaboration, making every sentence purposeful.

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?

Given the six parameters, output schema, and annotations, the description covers the key operational context: what the tool solves, what returns, and the critical freshness requirement. It does not discuss proxy usage or timeout, but those are well-documented in the schema, so the description is sufficiently complete for typical use.

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%, with detailed descriptions for all 6 parameters. The description reinforces the challenge freshness warning and gt reuse but adds minimal new meaning beyond the schema. Baseline of 3 is appropriate since the schema does the heavy lifting.

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?

Description clearly states 'Solve a GeeTest v3 slide-puzzle captcha', naming the specific captcha type and resource. It also specifies return values (geetest_challenge, geetest_validate, geetest_seccode), distinguishing it from sibling captcha-solving tools like reCAPTCHA and Turnstile.

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?

Provides explicit operational guidance: 'fetch gt and challenge from the page immediately before calling' and warns that a stale challenge is the most common failure. It does not explicitly contrast with alternative siblings, but the captcha-type-specific name and description give clear context for when this tool is appropriate.

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

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

With annotations already indicating readOnlyHint=false and destructiveHint=false, the description adds useful behavioral context: it returns recognized text and notes that proxies are unsupported. This goes beyond the structured annotations without contradicting them, providing operational expectations for the agent.

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 two sentences, front-loaded with the primary action and immediate use case. The second sentence provides a necessary limitation (proxy support) without any filler or redundancy. Every word contributes to understanding the tool's function and constraints.

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?

Given the simple parameter set (2 params, 1 required), full schema coverage, presence of an output schema, and annotations, the description covers the essential behavior, return value, and a key limitation. It could explicitly contrast with sibling captcha-solving tools, but the tool name and sibling list sufficiently fill that gap, making the description complete for the tool's scope.

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 input schema covers 100% of parameters with detailed descriptions for 'image' and 'timeout'. The description only reiterates that the image is a captcha, which is already evident from the schema. With full schema coverage, the baseline of 3 is appropriate; the description adds no significant semantic value beyond 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 clearly states the action: 'Read the text out of a distorted-text captcha image' with a specific resource and outcome. It distinguishes this tool from siblings by explicitly focusing on 'image captcha' versus Turnstile, reCAPTCHA, and Geetest, making the purpose unambiguous.

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 implies when to use it: when a distorted-text image captcha needs solving, and explains the result should be typed into the page's captcha field. It also provides a clear exclusion: 'Proxies are not supported for image captchas.' It does not explicitly name alternatives, but the sibling tool names and the 'image captcha' qualifier offer sufficient differentiation.

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

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

Annotations already mark the tool as non-readonly, non-destructive, and open-world. The description adds useful behavioral context: the token is placed in g-recaptcha-response before form submission, guessed sitekeys fail, and v3 scores are immutable. It does not describe potential external service requests or rate limits, but the openWorldHint and schema largely cover the interaction model.

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 three sentences and about 70 words, with no filler or repetition of schema details. It front-loads the main purpose, then packs in the key practical warnings. Every sentence contributes new information.

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?

Given the tool's complexity (9 parameters, nested proxy object, output schema) and the exhaustive input schema, the description covers all essential operational context: what it solves, what it returns, a critical prerequisite, and a fundamental limitation. It does not need to explain return values because an output schema exists, and it complements the rich schema and annotations well.

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 a baseline of 3 applies. The description adds meaningful parameter guidance beyond the schema by stressing that the sitekey must be read from the page (not guessed) and by noting v3's score cannot be raised, which affects expectations for the version/action parameters. This extra context justifies a score above baseline.

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 opens with a specific verb and resource: 'Solve a Google reCAPTCHA v2 or v3 widget, including invisible and Enterprise variants.' It clearly distinguishes itself from sibling tools (Turnstile, image captcha, Geetest) by naming Google reCAPTCHA and describing what it produces. The returned token's placement in g-recaptcha-response further clarifies its purpose.

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 provides a concrete prerequisite: 'Read the sitekey from the page first — a guessed sitekey fails.' It also warns about the v3 score limitation, helping agents know not to expect a higher score. It lacks an explicit 'use this instead of X' statement, but the sibling tool names and captcha-specific language make the context clear enough.

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

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

It discloses a critical behavioral constraint: the returned token must be submitted with the same userAgent or Cloudflare rejects it. It also clarifies when cdata/pagedata are required. These go beyond the annotations (readOnlyHint=false, openWorldHint=true) and are essential for correct use.

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?

Three tightly written sentences immediately convey purpose, output, and a high-priority caveat. No filler or repetition of schema fields; every sentence adds value.

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 7-parameter solver with a nested proxy object and an output schema, the description covers the essential behavioral nuances (widget vs interstitial, token-userAgent binding). The schema documents parameter details, and the output schema removes the need to explain return values, making the description complete for this complexity.

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 input schema already describes all seven parameters with 100% coverage, giving a solid baseline. The description adds extra meaning by tying cdata/pagedata to the interstitial challenge page scenario and explaining the userAgent token requirement, though it does not detail proxy or timeout semantics beyond 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 opens with a specific verb ('Solve') and resource ('Cloudflare Turnstile widget or interstitial challenge page'), and explicitly states the output (a token for cf-turnstile-response). This clearly distinguishes it from sibling captcha-solving tools (image, recaptcha, geetest).

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 provides clear usage context by distinguishing between widget and interstitial challenge page forms, and instructs passing cdata/pagedata for interstitial pages. It does not explicitly name alternatives or exclusions, but the sibling names make the intended use obvious.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description adds value by specifying what is being checked (running and reachable) and the diagnostic purpose. It does not introduce any surprising behavior, and there is no contradiction with annotations.

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 two sentences, front-loaded with the core purpose, and includes essential usage guidance. Every sentence contributes value with no 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?

For a simple status check with no parameters, an output schema, and read-only annotations, the description fully covers what the tool does, when to use it, and that it takes no arguments. No gaps remain.

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 tool takes no parameters, and the description explicitly states 'Takes no arguments,' which matches the empty schema. Baseline for 0 params is 4, and since no additional semantic detail is needed, this is appropriate.

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 clearly states the tool checks whether the CapSkip desktop app is running and reachable, using a specific verb and resource. It also distinguishes itself from sibling solving tools by framing this as a diagnostic pre-check.

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?

Explicit usage guidance is provided: 'Call this first when a solve fails unexpectedly' and it distinguishes between 'CapSkip is not running' and 'the sitekey was wrong'. This gives clear when-to-use context without needing to mention alternatives.

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