Server Quality Checklist

Tool Scores

• spider_screenshotC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only mentions the return format (base64 or binary) and ignores aspects like page loading, navigation, or automation actions, which are implied by the many parameters but not explained.

  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 exceptionally concise with two clear sentences: one stating the purpose and one stating the return format. Every word earns its place, and the front-loaded purpose makes it easy to scan.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity (19 parameters, nested objects, no output schema), this description is under-specified. It lacks any context on when to use the tool, how the many parameters interrelate, or what the return data looks like beyond base64/binary, making it insufficient for effective tool selection.

  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 schema has 100% parameter description coverage, so the baseline is 3. The tool description adds no extra semantic meaning beyond what the schema already provides, but it does not need to due to full schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool captures screenshots of web pages, which is a specific verb and resource. 'Screenshot' is distinct from sibling tools like spider_scrape or spider_crawl, but it does not explicitly contrast them, so it falls short of a perfect score.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or scenarios where this tool is preferred, leaving the agent without contextual direction.

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

• spider_searchC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It only mentions that it returns search results and optionally full page content, but omits any details about side effects, read-only behavior, rate limits, or operational traits. This is insufficient for a tool that likely performs network calls.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is only two sentences and front-loaded with the core purpose. However, the second sentence ('Returns search results with optional full page content') is partially redundant with the first ('optionally crawl results'), adding slight bloat but still keeping it concise.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 17 parameters, no output schema, and no annotations, this description is far too minimal. It doesn't explain the return format structure, how crawling works, what 'full page content' means, or how parameters like fetch_page_content, search_limit, or auto_pagination interplay. This leaves major gaps for an agent.

  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 schema has 100% parameter coverage, so the baseline is 3. The description itself adds no parameter-specific meaning; it doesn't mention any of the 17 parameters or how they affect behavior. But since the schema already documents each param, this is acceptable.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the tool as a web search with optional result crawling and full page content. The verb 'search' and resource 'web' are specific, and the optional full content distinguishes it from pure search. However, it doesn't explicitly differentiate from siblings like spider_crawl or spider_ai_search, so it's not a 5.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides no guidance on when to use this tool over other spider_* siblings. It doesn't mention alternatives or exclusions. The phrase 'optionally crawl results' could actually confuse usage with spider_crawl, making the guidance weak.

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

• spider_ai_searchB
  3.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It discloses a key behavioral constraint: requirement for an active AI subscription plan. However, it does not explain what happens if the subscription is absent, nor any other side effects, rate limits, or return behavior. This is useful but limited transparency.

  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 purpose and followed by the subscription requirement. Every word contributes value, and the structure is efficient. The all-caps 'REQUIRES' is a minor stylistic issue but does not detract from clarity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has 8 parameters, no output schema, and no annotations. The description explains what the tool does and the subscription requirement, but does not describe return format, result structure, error behavior, or how it differs from spider_search. For a search tool with this complexity, critical information is missing.

  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%, so the schema already documents all 8 parameters. The description adds no parameter-specific semantics, only general statements about intent understanding and relevance ranking, which apply to the tool's behavior overall rather than individual parameters. The baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states 'AI-enhanced semantic web search' and 'finds the most relevant results' using intent understanding and relevance ranking. It identifies the tool's specific verb (search) and resource (web), and the 'AI-enhanced' qualifier distinguishes it from the sibling spider_search, though it does not explicitly name the sibling. This is clear but slightly less explicit than the get_calls example.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description does not provide explicit usage guidance, such as when to use this tool versus spider_search or other siblings. It implies using it for AI-enhanced search but gives no comparison or 'when not to use' information. The subscription requirement is a prerequisite, not a usage guideline. This is a clear gap.

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

• spider_scrapeB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It claims 'No crawling' and 'one URL,' but the schema includes crawl-related parameters (sitemap, subdomains, budget, cron, whitelist, blacklist) and the URL parameter explicitly allows comma-separated multiple URLs, creating a significant misrepresentation. It also fails to mention important behaviors like proxy usage, cost multipliers, data storage, or output details beyond 'all output formats and screenshot.'

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is appropriately short and front-loaded with the main purpose, which is good for conciseness. However, the sentences do not earn their place: 'No crawling' is misleading, and 'Supports all output formats and screenshot capture' merely repeats information already in the schema. It is concise but not effectively informative, striking a balance between brevity and clarity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness1/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  This tool has 66 parameters, no output schema, and no annotations, yet the description is only two sentences. It fails to convey essential context like return formats, error handling, cost implications, proxy usage, or even the correct scope (single vs. multiple URLs). The description is grossly inadequate for a tool of this complexity and actively misleads about crawling capabilities.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  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, but the description actively contradicts the schema: it says 'one URL' while the schema states 'Can be comma-separated for multiple URLs,' and it says 'No crawling' while the schema includes crawl-related parameters. The description adds no useful parameter context and instead creates confusion, reducing its helpfulness below the 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 clearly states the tool's function with a specific verb and resource: 'Scrape a single page and extract its content.' It explicitly distinguishes itself from crawling tools by saying 'No crawling — just fetches and processes one URL,' which differentiates it from the sibling 'spider_crawl' tool. This is a clear, unambiguous purpose statement.

  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 clear usage context: use this for single-page scraping, not for crawling. The phrase 'No crawling' serves as an explicit exclusion, telling the agent when not to use this tool. However, it does not name the alternative tool (e.g., 'spider_crawl') or provide guidance on multi-page scenarios, so it lacks an explicit alternative recommendation.

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

• spider_crawlB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It only states return format and a promotional speed claim ('fastest web crawler'); it does not mention potential side effects like network cost, premium proxy multipliers, background execution, or external service dependencies. The schema descriptions cover some parameters, but the description itself lacks critical behavioral context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is only two sentences, front-loading the core purpose and output format. It is concise, but the phrase 'Powered by Spider - the fastest web crawler at 100K+ pages/sec' is promotional and adds little actionable information, though it does identify the external provider.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is highly complex (63 parameters, nested objects) and has no output schema. The description provides only a minimal high-level purpose and return format. While the schema descriptions are detailed, the overall description does not explain typical usage patterns, output structure, or how parameters interact, leaving the agent under-oriented for correct invocation and result interpretation.

  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% for all 63 parameters, so the schema thoroughly documents each parameter. The tool description adds no additional parameter semantics beyond what the schema already provides, hence the baseline score of 3.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action 'Crawl a website' and the scope 'extract content from multiple pages', giving a specific verb and resource. It implies differentiation from siblings like spider_scrape (which likely handles single pages), but does not explicitly name any alternative, so it stops short of full sibling differentiation.

  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 phrase 'from multiple pages' provides clear context for when to use this tool (multi-page crawling) versus alternatives. However, it does not explicitly mention when not to use it or name specific sibling tools, so it has context but no exclusions.

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

• spider_unblockerB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It does add useful context by mentioning 'enhanced fingerprinting and proxy rotation' and the extra cost of '10-40 extra credits per successful unblock.' However, it doesn't disclose failure behaviors, whether it bypasses robots.txt, or other side effects, so transparency is partial.

  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 long, front-loads the primary purpose, and every sentence adds value: purpose, method, and cost. No fluff or redundancy. It is appropriately concise.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite the tool's high complexity (66 parameters, no output schema, no annotations), the description is minimal. It lacks guidance on return format, failure handling, or when to prefer this over spider_crawl. For an AI agent to use this correctly in diverse scenarios, the description is insufficient.

  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 coverage is 100%, and all 66 parameters have individual descriptions in the schema, so the description doesn't need to compensate. The description adds no parameter-specific guidance beyond naming 'proxy' and 'fingerprint' mechanisms, which already appear as schema fields. Baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's core purpose: 'Access blocked or protected content with advanced anti-bot bypass.' This uses a specific verb and resource, and differentiates from siblings like spider_crawl by focusing on anti-bot bypass. However, it doesn't explicitly name alternatives, so it's not a perfect 5.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage for blocked or protected content, which provides context, but it doesn't explicitly state when to use this tool versus alternatives like spider_crawl, nor does it mention exclusions. This is implied guidance, not explicit.

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

• spider_linksA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It discloses a key behavioral trait ('without fetching content') and performance ('Fast'), but lacks details on return format, authentication, or limits. The disclosure is partial but adds some value beyond the tool name.

  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 with no fluff. It front-loads the core purpose and adds a practical use case, every word contributes.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given four parameters and no output schema, the description is minimal. It covers the basic purpose but omits information about return format, limit behavior, or how it handles dynamic pages. The description is sufficient for a simple tool but lacks depth.

  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%, so all four parameters (url, limit, request, return_format) are already documented. The description adds no extra parameter semantics, so the baseline score of 3 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 action (extract links), the resource (a page), and the key differentiator ('without fetching content'). It distinguishes spider_links from sibling tools like spider_scrape or spider_crawl.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies use for quick URL discovery ('Fast way to discover URLs on a site') but does not explicitly mention when to avoid it or suggest alternatives like spider_crawl or spider_search. Usage guidance is indirect rather than explicit.

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

• spider_get_creditsA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. The verb 'check' implies a read-only operation, but the description does not disclose whether this call consumes credits, requires authentication, or returns any specific format. Such details are minimal but valuable for an 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 a single, front-loaded sentence that directly states the tool's purpose. No wasted words or redundant details.

  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?

  For a simple zero-parameter, read-only operation, the description is nearly complete. It explains what the tool does but could add a note about whether the check consumes credits or what the response shape is, especially since there is no output schema.

  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 has zero parameters, so there is nothing to describe. The schema coverage is 100% (empty object), and the description adds no parameter semantics because none exist. Baseline 4 for zero-parameter tools 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 'Check your available Spider API credit balance' uses a specific verb ('check') and resource ('credit balance'), clearly distinguishing it from sibling tools that handle crawling, scraping, and other data operations.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The usage is implied by the purpose: this is a read-only balance check. However, the description does not explicitly state when to use it (e.g., before a large batch of operations) or mention that no alternatives exist among siblings.

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

• spider_ai_browserA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the full burden. It discloses a critical prerequisite ('REQUIRES an active AI subscription plan') but does not discuss operational behaviors such as navigation side effects, timeouts, or failure outcomes. This is a moderate amount of transparency for a nontrivial automation tool.

  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 long, with each sentence serving a distinct purpose: stating the core function, giving a usage example, and flagging the subscription requirement. It is front-loaded and contains no filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is complex (browser automation with natural language), yet the description omits details about expected output, rate limits, and how it compares to sibling tools. The subscription requirement and purpose are present, but the overall guidance is minimal for a tool with this 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 provides descriptions for all five parameters, achieving 100% schema_description_coverage. The description adds little beyond an example prompt, so the schema already carries the parameter meaning. Baseline 3 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 'AI-powered browser automation using natural language' and provides concrete examples ('click login, fill email, submit form'). This specific verb+resource distinguishes it from sibling tools like spider_scrape or spider_crawl, which focus on data extraction rather than interaction.

  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 gives clear usage context by showing how to phrase actions ('Describe actions like...'), implying this tool is for interactive tasks rather than retrieval. However, it does not explicitly mention alternatives or when not to use it, so it falls short of a 5.

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

• spider_ai_scrapeA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It does disclose the AI subscription requirement and the return format (structured JSON). However, it does not mention potential side effects like credit consumption, rate limits, or behavior on failure, which would be useful for a scraping tool. The description gives some key context but is not comprehensive.

  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 concise, consisting of two sentences that are front-loaded with the core purpose. It includes the essential subscription warning without unnecessary fluff, making it efficient and well-structured.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 6 parameters and a sibling (spider_scrape) that serves a similar function, the description is somewhat brief. It explains the AI-based approach and the subscription requirement but does not elaborate on output formats, limitations, or explicit comparison to non-AI scraping. The schema fills in parameter details, so overall completeness is moderate.

  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 coverage is 100%, so the baseline is 3. The description indirectly references the 'prompt' parameter ('Describe what data you want'), but it does not add significant meaning beyond the schema. It is adequate but not enhanced.

  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's function: 'AI-powered structured data extraction using plain English' and mentions it returns structured JSON without CSS selectors. This distinguishes it from sibling tools like spider_scrape, which likely requires selectors.

  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 context for when to use this tool: when you want to describe data in plain English rather than writing CSS selectors. It also mentions the prerequisite of an AI subscription. However, it does not explicitly name alternatives or state when not to use it, but the context is sufficient.

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

• spider_ai_linksA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses the AI requirement and the AI-driven behavior ('uses AI to find and categorize them'), but does not mention potential side effects, rate limits, or whether the operation is read-only. Given it's a link extraction tool, the lack of explicit safety disclosure is a minor gap, resulting in a 3.

  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 concise and front-loaded: three short sentences cover purpose, usage, and a critical requirement. There is no redundant information.

  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?

  The description provides enough context for an agent to understand the tool's purpose, usage, and a key constraint (AI subscription). It also hints at the output by saying 'find and categorize them'. With all parameters documented in the schema and no output schema, this is sufficient, though it does not explain return formats in detail.

  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?

  All parameters have schema descriptions, so the baseline is 3. The description's phrase 'Describe what links you want' adds a small amount of context for the 'prompt' parameter, but it does not elaborate on other parameters like 'limit' or 'return_format'. Schema coverage is 100%, so no further compensation is needed.

  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's function with specific verbs ('extraction and filtering') and describes the AI-powered approach. It distinguishes from sibling tools like spider_links by emphasizing AI and natural language prompts ('Describe what links you want').

  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 clear usage context: users describe what links they want. It also states a prerequisite (active AI subscription plan). However, it does not explicitly name alternative tools (e.g., spider_links) or exclusions, so it earns a 4 rather than a 5.

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

• spider_transformA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses a key behavioral trait—'No network requests'—which is important and distinguishes it from siblings. However, it does not describe output behavior, error handling, processing limits, or how multiple inputs are handled, leaving notable gaps.

  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 main action in the first sentence and a clarifying constraint in the second. Every sentence adds value with no filler or repetition.

  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?

  The combination of a complete schema and the description provides enough for an agent to understand the tool's purpose and key limitation (no network). The schema covers parameters, and the description supplies the critical distinction from siblings. However, without an output schema or annotations, it could have elaborated on response format or additional preprocessing behaviors, leaving minor gaps.

  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 already documents all 5 parameters with 100% coverage. The description only adds a high-level summary of formats, which aligns with the return_format enum but adds no new semantic information beyond the schema. Baseline 3 applies.

  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 uses a specific verb 'Transform' and identifies the resource as HTML content, listing target formats (markdown, text, other). It explicitly distinguishes itself from sibling fetch/crawl tools by stating 'No network requests — processes HTML you provide directly.' This makes it clear what the tool does and how it differs.

  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 the tool is for processing already-obtained HTML, contrasting with network-fetching siblings like spider_scrape or spider_crawl. It provides clear context for when to use it but does not explicitly name alternatives or state when not to use it, so it lacks explicit exclusions.

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

• spider_ai_crawlA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of disclosing behaviors. It discloses a key operational constraint—the mandatory AI subscription plan—which is not visible in the schema or annotations. It also states that the AI 'will guide the crawl,' signaling autonomous behavior. Yet it could elaborate on what happens without the plan or how AI decisions affect outcomes.

  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 exceptionally concise: two sentences and a URL. The core action and differentiator appear in the first sentence, with the subscription requirement in the second. Every word earns its place without redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 7 parameters, no output schema, and AI-driven behavior, the description is adequate but sparse. It covers the primary capability and the subscription prerequisite, but does not explain what a successful response looks like, how the prompt guides the crawl in practice, or any error/edge-case behavior. More context would improve operational confidence.

  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%, so the schema already documents all parameters clearly. The description adds a modest reinforcement of the 'prompt' role ('Describe what content to find and Spider's AI will guide the crawl'), but does not provide significant new parameter-level meaning beyond what the schema offers.

  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 uses a specific verb 'crawling' with a clear resource ('AI-guided') and method ('using natural language prompts'). It immediately distinguishes itself from the sibling tool 'spider_crawl' by emphasizing AI guidance and prompt-driven content discovery.

  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?

  It clearly establishes the usage context: when you need AI-guided crawling based on natural language descriptions. The explicit 'REQUIRES an active AI subscription plan' provides a critical prerequisite, implying that without such a plan this tool should not be used. However, it does not explicitly compare against alternatives like spider_crawl or state when to choose one over the other.

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