Server Quality Checklist

Tool Scores

• capskip_solve_geetestA
  4.2/5.0
  Behavior4/5

  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.

  Conciseness5/5

  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.

  Completeness4/5

  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.

  Parameters3/5

  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.

  Purpose5/5

  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.

  Usage Guidelines4/5

  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.

• capskip_solve_image_captchaA
  4.2/5.0
  Behavior4/5

  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.

  Conciseness5/5

  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.

  Completeness4/5

  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.

  Parameters3/5

  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.

  Purpose5/5

  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.

  Usage Guidelines4/5

  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.

• capskip_solve_recaptchaA
  4.5/5.0
  Behavior4/5

  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.

  Conciseness5/5

  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.

  Completeness5/5

  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.

  Parameters4/5

  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.

  Purpose5/5

  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.

  Usage Guidelines4/5

  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.

• capskip_solve_turnstileA
  4.7/5.0
  Behavior5/5

  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.

  Conciseness5/5

  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.

  Completeness5/5

  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.

  Parameters4/5

  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.

  Purpose5/5

  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.

  Usage Guidelines4/5

  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.

• capskip_statusA
  4.7/5.0
  Behavior4/5

  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.

  Conciseness5/5

  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.

  Completeness5/5

  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.

  Parameters4/5

  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.

  Purpose5/5

  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.

  Usage Guidelines5/5

  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.