Server Quality Checklist

Tool Scores

• describe_video_urlA
  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 discloses behaviors: temporary download to temp_media/ with deletion, YouTube cloud-read without download, public-only restriction, daily quota limits, per-second billing, unsupported platform errors, parameter precedence (prompt overrides persona/hint), and output characteristics. This is comprehensive beyond minimal expectations.

  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 an overview, bullet points, warning, parameter references, and returns. It is somewhat lengthy but every part adds necessary detail for a complex tool. The redundancy of listing parameters after saying they match describe_video is minor and acceptable for self-containment.

  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 no output schema and 6 parameters, the description is highly complete: it covers input formats, limitations, side effects, error cases, parameter dependencies, and return value format (with usage stats/truncation hints). No critical context is missing for an agent to invoke the tool correctly.

  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?

  Despite 0% schema_description_coverage, the description thoroughly explains every parameter: url supplies type specifications, prompt/persona/hint precedence, low_resolution purpose, and max_output_tokens default with 2048 lower-limit protection. This fully compensates for the schema's lack of 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 clearly states it downloads from a direct link or cloud-reads from a YouTube page, then sends to Gemini for Chinese timeline-segmented description. This distinguishes it from sibling describe_video by focusing on URL inputs, with explicit mention of supported URL types.

  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 provides clear context on when to use: direct video file links or YouTube page links. It also lists exclusions (Bilibili/Douyin/TikTok unsupported) and error behavior. However, it does not explicitly contrast with sibling describe_video beyond referencing it for parameter semantics, so a slight gap in direct alternative guidance exists.

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

• estimate_costA
  4.7/5.0
  Behavior5/5

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

  The description discloses the estimation method (prefer ffprobe, fallback to file-size estimate) and notes that approximations are marked. The readOnlyHint annotation is consistent, and the description adds meaningful behavioral context beyond the annotation without contradiction.

  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 clear purpose statement, a method note, and structured Args/Returns sections. Every sentence adds value, and it is appropriately front-loaded.

  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 one parameter and no output schema, the description is complete. It explains the input, the estimation logic, and the return value format, ensuring an agent can invoke it correctly without additional context.

  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?

  With schema description coverage at 0%, the description compensates by explaining that 'path' is a local video file path. While minimal, it clarifies the only parameter's role and local nature, which is sufficient for a single-param tool.

  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 purpose: estimating input token costs for sending a local video to Gemini. It uses a specific verb ('估算') and resource ('本地视频'), and is distinct from sibling tools like describe_video or get_upload_url.

  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 the tool ('让你发大视频前心里有数'), indicating it's for pre-upload cost estimation. It does not explicitly mention alternatives or when not to use, but the context is sufficient to differentiate from siblings.

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

• get_upload_urlA
  4.7/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, and the description adds behavioral context such as the return value (upload address and usage instructions) and the mode-dependent behavior. It discloses that the tool itself does not upload but returns an address, and explains the edge case where no endpoint exists.

  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: a one-sentence purpose, a numbered workflow, and a brief return summary. Every sentence adds value, with no filler or redundancy.

  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 zero-parameter utility, the description is complete: it explains the purpose, the exact HTTP POST usage, the expected response field (saved_path), and the follow-up calls to other tools. It also covers the local stdio mode limitation. No output schema exists, but the description adequately conveys return behavior.

  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 the schema fully covers parameter semantics. The description doesn't need to explain parameters; it instead explains the workflow and return value, which is appropriate for a 0-param tool. Baseline 4 per instructions.

  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 gets an upload URL to push files to the server for recognition. It uses a specific verb+resource and distinguishes itself from sibling tools like describe_video/view_media, which process files rather than provide upload access.

  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?

  It explicitly outlines when to use the tool (to move files from claude.ai chat/sandbox to the server) and provides a step-by-step workflow. It also notes a key limitation (local stdio mode has no upload endpoint), giving clear usage context without ambiguity.

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

• describe_videoA
  4.8/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries full burden. It discloses the upload to Gemini, conditional parameter interactions (prompt overrides persona/hint), internal token counting (thinking tokens count toward max_output_tokens), low_resolution speed tradeoffs, and return-value caveats (usage stats/truncation). This is very transparent.

  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 front-loaded with the core purpose, then organized into Args and Returns sections. Though lengthy, every sentence adds value—format support, parameter semantics, conditional overrides, and token behavior—without redundancy. It is efficiently structured for a complex tool.

  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 has no output schema, but the Returns section clearly describes the output. All parameter interactions, edge cases (e.g., 2048 token floor, thinking token consumption, environment variable), and behavioral notes (e.g., .gif not frame-sampled) are covered. The complexity is fully addressed; no gaps remain.

  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 explains all 6 parameters in detail: path (absolute path recommendation), prompt (overrides defaults and ignores persona/hint), persona (appends to default prompt only when prompt absent), hint (injects background context into default template), low_resolution (token rate tradeoff), and max_output_tokens (default, floor, thinking token interaction). This fully compensates for the missing schema 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 opens with a specific verb+resource: '把本地视频交给 Gemini 直传识别，返回按时间轴分段的详细内容描述（画面 + 音轨）'. It clearly states what the tool does (describes local videos via direct upload to Gemini) and distinguishes itself from the sibling 'describe_video_url' by emphasizing local file paths and direct upload.

  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 provides clear context on when to use: for local video files with supported formats (mp4/mov/webm/avi/mkv) and .gif. However, it does not explicitly mention when not to use it or name alternatives like describe_video_url, 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.

• view_mediaA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and excels: it discloses image downscaling to max_dimension, GIF first-frame-only behavior, video mid-frame fallback, the local ffmpeg prerequisite, and error return format ('Chinese explanation'). This goes well beyond a simple 'view media' statement.

  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 front-loaded with a one-sentence purpose, followed by well-separated sections for image vs. video behavior, tool differentiation, arguments, and return type. Every sentence earns its place; there is no fluff or repetition despite the detail.

  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?

  Despite lacking annotations and output schema, the description covers all needed context: return type (MCP ImageContent), error behavior, external dependency (ffmpeg), supported formats, scaling behavior, and runtime modes (stdio/HTTP). It also prevents misuse by referencing describe_video for animation/text needs, making it complete for both selection and invocation.

  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 properties have no descriptions (0% coverage), but the Args section adds rich meaning: path is a local file path, timestamp is video-only and measured in seconds, max_dimension has a default (1024), range (16–4096), and behavior (shrink only, never enlarge). This fully compensates for the schema's silence.

  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: 'return an image or a video frame as image content' to the calling model. It clearly distinguishes itself from the sibling tool describe_video by stating the division of labor: describe_video produces text, view_media returns the actual visual content.

  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 usage guidance is provided, naming describe_video as the alternative when a textual description is needed or when the whole GIF animation is required. It also clarifies when timestamp should be supplied for videos and the default behavior if omitted, making the decision boundary between tools unmistakable.

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