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

With no annotations, the description must carry the burden. It discloses the use of a 'local vision model' and provides the return JSON shape (text, mode, frames, duration). However, it does not explain behavior of different modes, potential limitations, or prerequisites. This is adequate but not rich.

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

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

The description is compact and front-loaded: two sentences. The first states the action and scope; the second gives the return format. No filler. The JSON example is dense but informative, and every element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters and no output schema, the description provides a return JSON structure, which is helpful. It lists capabilities and mentions modes. However, it does not explain the meaning of each mode or how frames are generated, leaving some gaps for a tool with this complexity.

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

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

Schema coverage is high (86%), with descriptions for most parameters (e.g., 'Video path / URL', 'Sampling frame rate'). The description adds some context by mentioning 'time-window deep reading' and 'contact sheets' which map to modes, but it does not significantly enhance parameter understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Analyze a video with a local vision model' and enumerates specific capabilities ('scenes, actions, time-window deep reading, contact sheets, etc.'). This distinguishes it from sibling tools like describe_image (image) and transcribe (audio), making it obvious this is for video analysis.

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

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

The description implies usage for video analysis but does not explicitly state when to use this tool over alternatives like describe_image or transcribe. There are no exclusions or direct comparisons to siblings. The context is clear for video tasks, but no explicit guidance is given.

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

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

No annotations are provided, so the description carries the burden. It discloses the local vision model usage and return JSON structure (text, mode, media), which adds useful context. However, it does not mention any side effects, limitations, failure modes, or permission requirements. As a read-only description tool, the risk is low, but behavioral details are minimal.

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

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

The description is two sentences: the first conveys the core purpose, the second gives the output format. It is concise, front-loaded, and every word earns its place with no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of annotations and output schema, the description still provides a clear purpose, output format, and parameter context via the schema. It is reasonably complete for a simple, read-only image description tool, but lacks usage guidance and edge-case information, so it is not fully complete.

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

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

The schema has 100% parameter coverage with clear descriptions (images, prompt, crop, size). The tool description adds no additional parameter semantics beyond stating the return JSON. Since the schema already documents each parameter thoroughly, the description is not required to compensate, hence a baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Describe or understand one or more images with a local vision model' and enumerates content types (scene, objects, colors, UI). This is a specific verb+resource pairing that distinguishes it from siblings like transcribe or analyze_video, which target audio/video.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. It never mentions the sibling tools or conditions like 'use for still images; use analyze_video for video'. Usage is only implied by the tool name and image-focused phrasing, which is insufficient for clear tool selection.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool returns JSON with text and, for videos, frame timestamps. It also clarifies the verbatim nature and lack of interpretation. It does not mention potential limitations like language support or file format restrictions, but the core behavior is well described.

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

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

The description is a single, front-loaded sentence that conveys the tool's essential purpose and return format with no wasted words. It packs key details (verbatim, media types, no interpretation, JSON output with timestamps) efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a moderate complexity with 2 parameters and no output schema, so the description must explain return values. It does mention the JSON structure and frame timestamps. However, it could be slightly more complete with details like supported file formats or default behavior for max_frames, but it's largely sufficient.

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

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

The input schema provides 100% coverage, with both parameters (media and max_frames) already described. The description adds minimal extra meaning beyond schema, only noting that videos get timestamps in the return JSON, which relates to max_frames but is not directly explained. Baseline 3 applies because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs verbatim transcription of text from images, documents, screenshots, and video subtitles. It distinguishes itself from siblings by emphasizing 'no summary, judgment, or interpretation', which sets it apart from describe_image and analyze_video.

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

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

The description provides clear context on what the tool does and implicitly indicates when to use it (extracting text verbatim) versus when not (when analysis or interpretation is needed). However, it does not explicitly name alternative tools like 'transcribe_audio' or 'describe_image', so it's clear but lacks explicit exclusions.

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

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

No annotations are provided, so the description carries the full burden. It discloses that it uses SenseVoice, includes timestamps, prefers embedded subtitles when available, and returns a JSON with 'text' and 'source' fields. This is meaningful behavioral context, though it does not cover failure modes or rate limits.

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

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

The description is two sentences, front-loaded with the core function, and the second sentence provides the return format. Every word earns its place; there is no wasted text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Considering the complexity (3 params, no output schema, no annotations), the description gives the key output format and subtitle preference, which helps the agent understand the tool's behavior. Minor gaps remain: no clarification of how 'transcribe' differs, and no details on timestamps format or error handling. Overall, it is sufficiently complete for basic invocation.

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

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

Schema description coverage is 67% (lang and media have descriptions; asr_model only has enum values). The description adds minimal parameter context by mentioning SenseVoice (the default model) and timestamps, but it does not explain asr_model options or lang choices beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs speech-to-text (FunASR SenseVoice, with timestamps), which is a specific verb and resource. It also mentions the output format, but it does not distinguish itself from the sibling tool 'transcribe', which could be ambiguous.

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

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

The tool implies usage for audio/video files needing transcription and notes that embedded subtitle tracks are preferred when available, hinting at when subtitles might be used. However, it does not explicitly state when to use this tool over the 'transcribe' sibling or provide any exclusions.

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

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

No annotations are present, so the description carries full responsibility. It usefully warns that the operation can be slow and lists the types of checks performed. However, it does not disclose output format, side effects, or failure behavior, which would be valuable for a diagnostic tool.

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

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

The description is a single, front-loaded sentence: it states the action and then adds scope and a performance cue in a parenthetical. Every word earns its place, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The scope is clear, but the description does not explain what the health check returns (e.g., a pass/fail status, detailed results, or metrics). Since there is no output schema, this leaves the agent uncertain about how to interpret the result. Still, for a zero-parameter tool, it is reasonably adequate.

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

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

The tool has zero parameters, so the schema trivially covers everything. The description adds no parameter-specific meaning, but the baseline of 4 for no-parameter tools is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('run') and resource ('environment health check'), and enumerates the covered capabilities (image reading, transcription, video sampling). This distinguishes it from the sibling tools, which each handle a single capability.

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

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

The usage is implied by the description: this is the aggregate health check tool. However, it does not explicitly state when to prefer this over the individual tools like describe_image or transcribe, nor does it mention any alternatives or exclusions.

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

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

With no annotations provided, the description carries the full burden. It discloses the tool shows status information and lists key aspects, implying a read-only operation, but it does not explicitly confirm no side effects, required permissions, or possible failure behavior.

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

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

The description is a single, front-loaded sentence with a concrete list of what the status includes. There is no redundant information or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter status tool with no output schema, the description adequately scopes the tool by naming the exact aspects (models, backend type, ffmpeg, speech environment, GPU, watchdog). It omits return format but this is not critical for a status check.

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

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

The tool has zero parameters, so there is no parameter semantics to clarify. Baseline 4 applies; the description correctly omits parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Show' and resource 'vision backend status', and enumerates the included components (models, ffmpeg, GPU). This clearly distinguishes it from sibling tools like describe_image or transcribe, which serve different purposes.

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

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

The description implies a diagnostic use case for inspecting backend status but does not explicitly state when to use this tool vs alternatives like vision_check. No exclusions are mentioned, so guidance is only implied.

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