Server Quality Checklist

Tool Scores

• fetch_pageA
  3.5/5.0
  Behavior3/5

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

  The description mentions stealth mode and a 50,000 character truncation, adding some behavioral context. However, it does not disclose error handling, rate limits, authentication needs, or what happens on failure, leaving gaps for an AI 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-loading the core action and listing key features. Every sentence adds value with no redundant or vague phrasing.

  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 description covers extraction modes and truncation but omits return format (e.g., plain text, HTML), error scenarios, and guidance on the wait_for parameter. For a tool with an output schema missing, more detail on output and behavior would be beneficial.

  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% (all parameters described), so the baseline is 3. The description adds truncation limit and extraction mode types, but this context is partially redundant with the schema's enum for extract_mode. No additional per-parameter semantics are provided.

  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 it fetches and extracts content from a web page using Playwright with stealth mode, listing specific extraction modes. This distinguishes it from sibling tools like search_internet, which perform web searches, and execute_python, which runs code.

  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?

  No guidance is provided on when to use this tool versus alternatives. The description lacks explicit context on when to use fetch_page over search_internet or other tools, and does not mention prerequisites or limitations.

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

• execute_pythonA
  3.7/5.0
  Behavior3/5

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

  No annotations provided. Description covers sandbox details (network disabled, resource limits) and auto-install behavior, but does not disclose return format, error handling, or output structure.

  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?

  Two sentences with no redundancy. First sentence encapsulates core purpose and constraints, second adds key behavior (auto-install).

  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?

  Covers security and auto-install but omits return value description and error behavior. With no output schema, agents lack full understanding of tool's response.

  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% with detailed parameter descriptions. Description adds 'auto-detects missing packages' for the code parameter, which is a nice extra but not essential.

  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 it executes Python code in a sandbox with security constraints. It is distinct from sibling tools (fetch_page, search) which are for web data retrieval.

  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 safe Python execution but lacks explicit when-to-use or alternatives guidance. No mention of prerequisites or exclusions.

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

• search_internetA
  3.8/5.0
  Behavior4/5

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

  Despite no annotations, the description discloses deduplication, same-domain limiting, conditional filtering of low-trust domains, and three search modes (speed, balanced, quality), providing reasonable insight into behavior.

  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 concise sentences, front-loaded with the main purpose, then expanding on return format, modes, and filtering. No unnecessary words.

  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 no output schema or annotations, the description covers return fields, deduplication, domain limits, and modes. Lacks error handling and mode effects detail, but is largely complete for a search tool.

  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% with descriptions for all parameters. The tool description adds no new parameter-level meaning but mentions deduplication and domain limits as behavioral context beyond 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 defines the tool as searching the internet via SearxNG, listing returned fields (title, URL, snippet, source engine, score) and distinguishing it from siblings like fetch_page or get_search_suggestions.

  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?

  No explicit guidance on when to use or not use this tool versus siblings (execute_python, fetch_page, get_search_suggestions). The description lacks context for appropriate usage scenarios.

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

• get_search_suggestionsA
  4.2/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the burden. It discloses fallback behavior (simple query expansion) and return type, but does not explicitly state that it is read-only or discuss side effects.

  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?

  Two concise sentences, front-loaded with purpose, no wasted words.

  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?

  Although no output schema, the description adequately explains the return format (suggestion strings) and key behaviors. Could be slightly more explicit about the array structure, but overall sufficient for a simple tool.

  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 coverage is 100% but the description adds value by clarifying the 'query' is partial and that 'max_suggestions' controls the number of returned strings.

  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 it gets autocomplete suggestions from SearxNG for partial queries, and implicitly distinguishes from sibling tools like search_internet which handles full queries.

  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 indicates when to use (for autocomplete suggestions) and mentions fallback behavior, but does not explicitly contrast with alternatives like search_internet for full queries.

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