Server Quality Checklist

Tool Scores

• brave_image_searchA
  3.6/5.0
  Behavior2/5

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

  Annotations only provide 'openWorldHint: true', which signals non-destructive but no further details. Description adds a markdown display tip but lacks disclosure of rate limits, authentication needs, pagination specifics, or error 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?

  Two concise sentences: first states purpose, second offers usage advice. No wasted words, front-loaded with key 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?

  Output schema exists, so return values are covered. Description adds practical usage advice (markdown images) and covers the tool's typical context. Could mention pagination via 'offset' (covered in schema) but otherwise complete for a simple 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 description coverage is 100%, so the schema already explains all parameters. The description does not add additional parameter-level meaning beyond what is in the schema, earning a baseline score.

  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?

  Clearly states action ('performs an image search') and resource ('Brave Search API'). Provides specific examples of use cases (pictures, design, art) and implicitly distinguishes from sibling tools like web, local, news searches.

  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?

  Gives examples of when to use ('when you need pictures...') but does not explicitly state when not to use or mention alternatives. The sibling list helps, but the description itself lacks direct guidance on differentiation.

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

• brave_news_searchA
  3.9/5.0
  Behavior3/5

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

  Annotations only include title and openWorldHint (unclear). The description adds behavioral info: returns JSON list with title, url, description, and snippets. No contradictions, but no disclosure on rate limits or authentication. Since annotations are minimal, the description provides adequate but not rich 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 somewhat lengthy but well-structured into sections (purpose, when to use, result format, examples). It is front-loaded with the core purpose. Could be slightly more concise, but generally clear and organized.

  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 11 parameters, no output schema, and no nested objects, the description explains the return format (JSON list with title, url, description, snippets) and provides usage guidance. It covers essential context but could mention pagination more explicitly (offset and count).

  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 covers 100% of parameters with descriptions, so the description does not need to add much. It summarizes query and result format, but adds no new parameter details beyond the schema. 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 it searches for news articles using Brave's News Search API. It distinguishes from sibling tools (other Brave searches) by specifying 'news' and providing usage examples, making the purpose specific and 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 includes a 'When to use' list that explicitly guides the agent on appropriate scenarios (e.g., finding recent news, breaking updates). It also provides markdown citation examples. While it lacks explicit 'when not to use', the positive guidance is strong and contextually clear.

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

• brave_video_searchA
  4/5.0
  Behavior3/5

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

  Annotations include openWorldHint=true, indicating external data access. The description adds return format details (title, url, description, etc.) but does not discuss rate limits, authentication, or potential side effects. It provides moderate transparency beyond 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 concise and well-structured, with a clear opening sentence, a bulleted usage section, and a brief return format note. No unnecessary content, and every sentence adds value.

  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 adequately covers the main purpose and return format for a video search tool with 9 parameters. However, it lacks details on error handling, pagination behavior beyond what the schema provides, and more comprehensive output structure. Still, it is mostly 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?

  The input schema already covers all 9 parameters with descriptions (100% coverage). The tool description does not add substantive parameter-level information beyond what the schema provides, so a 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 it searches for videos using Brave's Video Search API, specifying the resource (videos) and the action (searches). It distinguishes itself from sibling tools like brave_web_search and brave_image_search by explicitly focusing on video results.

  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 includes a 'When to use' section that provides clear context for video discovery, but does not explicitly state when not to use it or list alternatives among siblings. The context is sufficient given the distinct purpose.

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

• brave_web_searchA
  4/5.0
  Behavior3/5

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

  Annotations only include 'openWorldHint: true', so the description carries more burden. It discloses return format (JSON list with title, description, URL) and that results can vary based on 'results_filter'. It doesn't discuss rate limits, authentication, or any side effects beyond consumption of the API. Adequate but not thorough.

  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, well-structured with a main sentence, bullet points for use cases, and a note about 'results_filter'. 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?

  For a web search tool with 15 parameters and no output schema, the description covers the purpose, use cases, and key behavioral notes. It could mention that it requires network access (implied by openWorldHint) or pagination behavior, but overall it's fairly complete.

  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 parameters are fully described in the schema. The description adds minimal extra meaning, only noting the effect of 'results_filter' on result types. Baseline 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 it performs web searches using Brave Search API and lists diverse use cases (general, location, news, videos). It distinguishes from sibling tools by mentioning that when 'results_filter' is empty, results may include FAQ, Discussions, News, and Video, which are normally handled by separate siblings.

  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 'When to use' section provides explicit scenarios. It also notes behavior when 'results_filter' is empty, implying when to expect additional result types. However, it does not explicitly mention when NOT to use this tool or list alternatives like brave_local_search or brave_video_search.

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

• brave_llm_contextA
  4.1/5.0
  Behavior4/5

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

  Annotations include openWorldHint: true. The description adds value by detailing the return types (text chunks, tables, code blocks, structured data) and mentioning citation of source URLs. No contradictions or missing behavioral traits are evident.

  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 well-structured with bullet points for usage and a clear opening statement. It is moderately long but every sentence adds value. Slight trimming could enhance conciseness.

  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 tool's complexity (26 parameters, output schema exists), the description provides a high-level overview and usage context. It does not need to detail return values due to output schema. It covers key aspects but could briefly mention output schema existence.

  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 parameters are documented. The tool description provides no additional parameter meaning beyond what is in the schema. 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 the tool retrieves pre-extracted, relevance-ranked web content via Brave's LLM Context API, optimized for AI agents, LLM grounding, and RAG. It distinguishes itself from traditional search by returning actual page content rather than just links.

  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 explicitly lists use cases: grounding answers, AI agent content, question answering, fact-checking, research, and when page contents are needed. It implicitly suggests not using when links suffice, but lacks explicit 'when not to use' statements.

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

• brave_place_searchA
  4.1/5.0
  Behavior3/5

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

  The description discloses that radius is a bias not a hard limit and explains location format. However, it does not address rate limits, authentication, or other behavioral nuances, missing some transparency beyond the openWorldHint annotation.

  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 well-structured with bullet points and front-loads the main purpose. While slightly lengthy, every sentence serves to clarify behavior or usage, with 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?

  Given the 17 parameters and output schema existence, the description covers essential usage patterns and constraints. It lacks error handling details but provides sufficient context for an AI agent to select and invoke the tool effectively.

  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%, so baseline is 3. The description adds significant value by explaining inter-parameter dependencies (e.g., anchor required for addresses/streets, query behavior when omitted) and clarifying the radius's non-hard-limitation, going beyond the schema's individual parameter descriptions.

  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 ('Searches Brave's Place Search API') and clearly differentiates the various result types (POIs, cities, addresses, streets, location) based on query shape, making the tool's 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?

  A dedicated 'When to use' section provides clear scenarios for each result type. It explains input requirements (anchor via lat/long or location) and constraints (addresses/streets require specific query shape), though it does not explicitly compare to sibling tools.

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

• brave_local_searchA
  4.5/5.0
  Behavior4/5

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

  Discloses the Pro plan requirement and fallback behavior. Annotations only provide openWorldHint, which is not contradicted; tool appears read-only. Could mention rate limits or auth specifics, but provides good context.

  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?

  Well-structured with clear sections, bullet points for return fields, and front-loaded with key access info. No wasted words.

  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 15 parameters and no output schema, the description covers purpose, restrictions, fallback, typical use cases, and output format (ratings, addresses, etc.), making it complete.

  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 parameters are well documented in the schema. The description does not add significant new meaning beyond the schema's descriptions, meeting 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 it is for location search, listing specific use cases like businesses and restaurants, and distinguishes from sibling tools like brave_web_search and brave_place_search.

  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?

  Explicitly tells when to use (location queries, 'near me'), when not (non-Pro plan users should use brave_web_search), and mentions automatic fallback to brave_web_search.

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

• brave_summarizerA
  4.6/5.0
  Behavior5/5

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

  Annotations only include openWorldHint: true. The description adds key behavioral context: it requires a Pro AI subscription, depends on prior brave_web_search, and returns a text summary with optional features. No contradictions 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.

  Conciseness4/5

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

  The description is well-structured with a clear first sentence stating purpose, followed by usage guidelines, return description, and requirements. It is slightly lengthy but every sentence adds value, so concise enough.

  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 3 parameters, no output schema, and minimal annotations, the description is thorough. It covers prerequisites, subscription requirements, return format, and optional features. Missing nothing essential for tool selection and 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 100%, so baseline is 3. The tool description repeats the optionality of entity_info and inline_references but does not add new meaning beyond the schema. Minor clarification but insufficient to raise score.

  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 retrieves AI-generated summaries of web search results, specifying the verb (retrieves) and resource (summaries). It distinguishes from sibling search tools by emphasizing the summarization function and prerequisite dependency on brave_web_search.

  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 'When to use:' bullet points list specific scenarios. It also states requirements: must first call brave_web_search with summary=true and need a Pro AI subscription, providing clear context and exclusions.

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