Server Quality Checklist

Tool Scores

• fetchA
  3.5/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently lists the return fields (url, final_url, content_type, text, byte_count) and mentions an error field with a stable string code. However, it does not discuss cleaning behavior, redirects, timeouts, size limits, or other operational details that could affect usage.

  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 well-structured: a single sentence stating the core behavior, followed by an Args block and Returns block. Every sentence provides necessary information without fluff, and the most important information (what the tool does) is front-loaded.

  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 relatively simple, and the description provides a clear functional overview and return contract. However, it lacks usage guidance relative to sibling tools and does not define the 'stable string code' values or content type semantics. Given the low annotation coverage and the existence of sibling tools, the description is adequate but incomplete for fully-informed invocation.

  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 0%, so the description must compensate. It does explain the 'url' parameter as requiring an http:// or https:// URL, which adds meaning beyond the schema. However, the 'ctx' parameter is not described at all, leaving a gap in parameter understanding.

  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: 'Fetch a URL and return its cleaned main text content.' This is a specific verb+resource combination that distinguishes it from siblings like search, scrape_blog, and deep_scrape by emphasizing the 'cleaned main text' output.

  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?

  There is no explicit guidance on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or comparisons to sibling tools. It only provides the purpose and return format, leaving usage context entirely to the agent.

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

• searchA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses defaults for categories, language, pageno, safesearch, max_results, valid time_range values, and error behavior. It doesn't mention rate limits or authentication, but for a search tool this is adequate 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 well-structured with Args and Returns sections. Every sentence carries useful information—no fluff. The length is appropriate given the parameter count.

  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?

  The description covers all parameters, return value structure, error handling, and default behaviors. Even with an output schema present, it adds clarity. It is complete for a web search tool.

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

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, but the description compensates by explaining every parameter's purpose, allowed values, and defaults. This adds substantial meaning beyond the bare input 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 'Search the web via the configured SearXNG instance,' using a specific verb + resource. This distinguishes it from siblings like fetch and scrape_blog, which are about retrieving specific pages or content, not general search.

  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 purpose is clear and implies when to use it (when conducting a web search), but it doesn't explicitly mention when not to use it or alternatives. However, the sibling tool names (fetch, scrape_blog) make the distinction self-evident.

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

• deep_scrapeA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and does so excellently. It discloses output file paths, per-post and per-document error handling (failures noted in-band), the document count cap, binary asset location, and the exact return dict shape including failure modes. This is far beyond typical 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?

  Although lengthy, the description is well-structured with clear sections (overview, discovery, output paths, error handling, args, returns). Every sentence adds meaningful information, and the formatting (code blocks, bullet lists) aids readability without waste.

  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?

  The tool is complex with many behaviors, but the description fully covers inputs, outputs, error semantics, file paths, and even operational limits. The output schema is also provided, but the description redundantly explains the return dict, which is acceptable given the richness. No critical gaps exist.

  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 has 0% description coverage, but the tool description explains the required parameter blog_url ('Root URL of the blog') and adds essential behavioral context (e.g., the deep_scrape_max_documents_per_blog env var). However, the optional 'ctx' parameter is left unexplained, and no details are given about its expected format or purpose.

  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 specific verbs ('Discover', 'fetch', 'download + extract') and clearly identifies the resource (blog posts and linked documents). It explicitly distinguishes itself from the sibling tool scrape_blog by describing the additional document handling, 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 clearly states the tool's scope ('Same discovery as scrape_blog' plus document extraction) and provides detailed behavior, but it does not explicitly say when to prefer this over scrape_blog or under what conditions to avoid it. The context strongly implies the usage distinction, but a direct when/when-not statement is missing.

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

• scrape_blogA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description fully carries the behavioral burden. It discloses the two-phase discovery strategy, parallel fetching, output file location and naming, YAML front matter contents, in-band error handling ('- Fetch error: <code> bullets, not by aborting'), and that the return value is a summary dict, never the file contents. This is exemplary 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 long but every sentence earns its place, covering purpose, algorithm, output format, error handling, arguments, and return value. It is front-loaded with the core purpose and uses structured headings (Args, Returns) for scannability.

  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 tool with two parameters, no annotations, and an output schema, this description is remarkably complete: it explains discovery limits, output path, file structure, in-band error behavior, and the exact return dict on both success and failure. It leaves no critical operational gap.

  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 0%, so the description must compensate. It explains the only meaningful parameter, blog_url, with type, purpose, and an example. The ctx parameter is auto-injected and left unexplained, but this is acceptable; the description adds substantial meaning beyond the sparse 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+resource+action: 'Discover every post on a blog and write a single aggregated Markdown file.' It clearly distinguishes this from sibling tools like fetch (single-page fetch) and search (web search) by emphasizing blog-wide discovery and file output.

  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 use case: use this when you want all posts from a blog aggregated into one Markdown file. It details the strategy (RSS/Atom first, then HTML crawl) but does not explicitly state when to prefer this over alternatives or when not to use it, so it falls just 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.