Server Quality Checklist

Tool Scores

• audioA
  3.6/5.0
  Behavior3/5

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

  The description adds the behavioral constraint that the server will not reclassify the source, which is useful. However, annotations already indicate readOnly and destructive hints, and the description does not disclose potential error behaviors, output format, or handling of non-audio inputs beyond the lack of reclassification.

  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 short sentences, front-loaded with the main purpose, and contains no fluff. Every phrase earns its place, making it highly concise and well-structured.

  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?

  With full schema coverage and annotations, the description is adequate for a simple single-source tool. It lacks details on output format or accepted audio formats, but these are not critical given the tool's simplicity and the prompt parameter's flexibility.

  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 documents all three parameters. The description adds no additional parameter meaning beyond what the schema already states, such as mentioning 'local path' and 'URL' which are already described in the source property.

  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 states it 'understand[s] one audio source from a direct remote URL or local path,' which identifies the resource and source types. However, the verb 'understand' is broad and not as specific as 'analyze' or 'transcribe,' and it doesn't fully distinguish from sibling tools beyond the modality mention.

  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 by saying 'The caller chooses this modality; the server does not reclassify the source,' which tells the caller to select this tool only for audio. It does not explicitly mention alternatives or exclusions, so 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.

• videoA
  3.9/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered without description. The description adds meaningful behavior: the tool accepts exactly one video source and never reclassifies the caller-selected modality, which is a non-obvious quirk beyond the annotations. It does not contradict any annotation.

  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, front-loaded with the core purpose, and each clause contributes either input constraints or the no-reclassification caveat. There is no filler or redundant restatement of the schema.

  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 three-parameter tool with rich schema descriptions and safe-read annotations, the description covers input modes and the key behavioral quirk. It does not describe the return format, but no output schema exists and the prompt schema implies a text-based Gemini response, so the missing piece is minor.

  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 still adds value by specifying that 'source' can be a public YouTube URL, a direct remote video URL, or a local video path, and by clarifying that the caller controls the modality. This enriches the generic 'public HTTP(S) URL' schema text and reinforces prompt/mimeType intent.

  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 uses a specific verb+resource ('Understand one video source') and enumerates accepted source types (YouTube URL, direct remote video URL, local video path), which clearly maps to the video modality among siblings. It does not explicitly contrast with sibling tools, but the resource type and tool title make 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 Guidelines3/5

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

  The description states valid input forms and warns that the caller must choose the modality because the server will not reclassify the source, giving some context on source selection. It does not explicitly say when to prefer this tool over web/audio/document/image siblings, so usage guidance is implied rather than explicit.

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

• imageA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds behavioral context beyond annotations: it explicitly states that the server does not reclassify the source, setting expectations about how the tool handles input types. This is useful transparency that the annotations alone do not convey.

  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 long, front-loaded with the main purpose, and the second sentence clarifies a key behavioral limitation. No unnecessary words or repetition of schema details. Excellent 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?

  For a simple tool with rich schema descriptions and annotations, the description covers the essential context: what it does, the input types, and the no-reclassification behavior. It does not describe output format, but no output schema exists and the prompt parameter implies free-form text responses. It is complete enough for an agent to select and invoke the tool correctly.

  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 100% parameter description coverage, with clear explanations for source, prompt, and mimeType. The tool description itself does not add new parameter semantics, but the schema already does the heavy lifting. Baseline 3 is appropriate here.

  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's purpose: to understand an image from a direct remote URL or local path. It distinguishes from sibling tools by emphasizing that the caller chooses the modality and the server does not reclassify the source. 'Understand' is somewhat generic, but the context of Gemini image understanding and the explicit source scope make it clear.

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

  Usage Guidelines4/5

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

  The description provides clear usage context by stating 'The caller chooses this modality; the server does not reclassify the source.' This tells the user to use this tool when they have an image source and not to expect auto-detection of non-image inputs. It implicitly differentiates from sibling tools (web, video, audio, document) without naming them explicitly.

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

• documentA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful behavioral context: the server does not reclassify the source, and local paths are resolved on the MCP server. This complements the annotations without contradicting them.

  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-loads the purpose ('Understand one document source'), and includes only essential details about modality selection and source resolution. No fluff or redundancy.

  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 read-only tool with no output schema, the description and schema sufficiently cover the input source, prompt, and optional MIME hint. It does not describe the return format, but the prompt's schema (determine/extract/summarize) implies a text response, so the overall picture is 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 description coverage is 100%, so the schema already documents all three parameters. The description restates source types (URL/path) but adds no new parameter-specific semantics beyond what the schema provides, earning the baseline 3.

  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 the specific verb 'understand' and resource 'document source', enumerates example types (PDF, CSV, text) and source kinds (URL or local path). It also differentiates from sibling tools by stating the caller chooses the document modality, making its scope 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?

  It clearly scopes the tool to document sources and implies that other modalities have dedicated tools. However, it does not explicitly name alternative tools or state 'use web for URLs to web pages', so it stops short of fully explicit when-not-to-use guidance.

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

• webA
  4.5/5.0
  Behavior4/5

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

  The annotations already declare readOnlyHint and openWorldHint, but the description adds context about enabling Google Search and URL Context, and clarifies that prompts should contain URLs. This is meaningful behavioral information not present in the annotations, though it does not cover potential limitations or output format.

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

  Conciseness5/5

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

  Three sentences, each delivering essential information: what the tool does, how to format prompts, and when to use alternatives. 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 simple single-param tool with no output schema, the description provides sufficient context about tool behavior and usage boundaries. The annotations cover safety profile, and the description covers usage and alternatives, 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?

  The schema already describes the 'prompt' parameter as 'A web question or instruction, including any ordinary webpage URLs,' so the description's mention of putting URLs in the prompt largely restates the schema. The description does not add new parameter-specific details beyond confirming the text-based nature, and the guidance about media inputs relates to sibling tools rather than the prompt parameter.

  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 uses Gemini with Google Search and URL Context for web research, and explicitly directs media/file inputs to sibling tools (video, audio, document, image), distinguishing it from them. The verb 'Use' is supported by the resource 'Gemini with Google Search and URL Context'.

  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?

  The description explicitly instructs to put ordinary webpage URLs directly in the prompt and tells users to use video, audio, document, or image for typed media and file inputs, naming the alternatives. This provides clear guidance on when to use this tool versus its siblings.

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