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

No annotations are provided, so the description must disclose behavior. It mentions the model (Qwen3-ASR) and formats, but does not mention side effects, requirements, or return behavior. For a transcription tool, it's likely safe, but this is not explicitly stated.

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 concise: a short intro plus a well-formatted args list. Every sentence adds value (formats, model, parameter meanings) 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 tool is simple, has an output schema, and the description covers core aspects like formats and model. It lacks explicit guidance on when to use vs alternatives, but overall it is adequate for a transcription tool.

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 0% description coverage, but the description lists all four parameters with meaningful explanations, including allowed values for language (auto|zh|en|ja|ko) and output_format (json|txt). This compensates well for the schema's minimal parameter descriptions.

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 '音频转写' (audio transcription) with a specific verb and resource, and lists supported formats (wav/mp3/m4a/flac). It is unambiguous and obviously distinct from the sibling vision/GUI tools.

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 by specifying supported audio formats and the transcription context. It does not explicitly state when not to use or alternatives, but the siblings are clearly different, making the intended use clear.

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 bears full responsibility for behavioral disclosure. It mentions the use of MinerU or PaddleOCR engines and output formats, but does not state whether the operation is read-only, if network access is required, or any error-handling 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 concise and well-structured: a single purpose sentence followed by a parameter list. Every sentence earns its place, and the primary function is front-loaded.

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 description covers all parameters, supported input formats, engine options, and output formats. It lacks details on prerequisites or edge cases, but since an output schema exists, return-value details are not needed here.

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?

All 7 parameters are described with meanings and examples (e.g., pages '1-20', engine choices, boolean flags). This adds substantial value beyond the input schema, which only lists titles and defaults without descriptions.

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 opening line clearly states the tool's function: 'Parse documents (PDF/DOCX/PPTX/XLSX/images) into Markdown/JSON'. This specifies a verb, resource types, and output formats, making it distinct from sibling tools like audio_transcribe or video_index.

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 lists supported file formats (PDF/DOCX/PPTX/XLSX/images), giving clear context on when to use this tool. It does not explicitly mention alternatives or exclusions, but sibling tools cover other media types, making the intended use evident.

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 high-risk actions require a confirmation token, which is valuable behavioral context. However, it does not mention potential side effects (e.g., navigation, state changes) or prerequisites like session validity. The token requirement is the only explicit behavioral trait.

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 concise: a one-line summary followed by a clean parameter list. Each item earns its place, and the structure is easy to scan. No fluff or redundant information.

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 10 parameters and no annotations, the description covers all parameters and includes a safety note about high-risk actions. The output schema exists, so return values need not be described. Minor gaps remain, such as clarifying which actions are exactly 'high-risk' and whether a session must already exist, but overall it is sufficient 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.

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

The description explicitly explains every parameter in the schema, including target, session_id, action, selector, x, y, text, url, reason, and confirm_token. It adds context by specifying allowed values for action and target, and clarifies that confirm_token is required for high-risk actions. 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.

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

The description clearly states '执行 GUI 动作' (Execute GUI actions), with a specific verb and resource. It enumerates target types and action types, distinguishing it from the sibling tool gui_observe which is for observation. The scope is explicit.

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 by naming targets and actions, but provides no explicit guidance on when to choose this tool over alternatives (e.g., gui_observe). It mentions the confirm token requirement for high-risk actions but does not compare with sibling tools. Context is present but alternatives are not addressed.

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 is the sole source of behavioral information. The verb '观察' (observe) implies a read-only operation, and the description states it returns a screenshot and status, which is useful. However, it does not explicitly confirm non-destructiveness, mention any side effects on the target system, or disclose prerequisites like requiring an active session. It adds some context beyond the schema but lacks full transparency.

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 well-structured: a one-sentence purpose followed by a concise ARGS list. Every line provides necessary information with no filler or repetition. It is appropriately sized for the tool's complexity and front-loaded with the primary behavior.

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 an output schema exists (though not shown), the description need not enumerate return fields in detail. It mentions the key return type (screenshot, status) and parameter effects. It could further explain session semantics or real-time capture behavior, but for a straightforward observation tool the coverage is adequate. Missing explicit mention of read-only behavior is slightly mitigated by the verb 'observe'.

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 provides only titles and defaults with zero descriptions, so the description's Args section carries the full semantic weight. It explains each parameter's meaning, including the allowed values for 'target' (browser|android|macos), the purpose of session_id, and booleans for screenshot and accessibility tree inclusion. This is a strong complement to the schema, adding critical context where the schema is silent.

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?

Description clearly states it observes GUI targets (browser, Android, macOS) and returns screenshots and status info. It uses a specific verb 'observe' and names distinct resources, which distinguishes it from mutation tools like gui_act. However, it doesn't explicitly differentiate from vision-related sibling tools such as vision_inspect, so it's not fully distinct.

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 gives no guidance on when to use this tool versus alternatives like vision_inspect or health_check. There are no exclusions or context cues for choosing this over other observers/monitors. The intended use is implied by the name and primary sentence, but explicit usage guidance is absent.

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, the description carries the full burden. It does disclose that deep=true involves actual API calls to verify vision capability, which is a meaningful behavioral detail. However, it does not state whether the tool is read-only, what the return structure is, or whether network access is required. The transparency is moderate.

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 concise, with a single front-loaded sentence stating the tool's purpose, followed by a clear Args section for the parameter. No unnecessary prose.

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 description covers the core purpose and the one parameter well. Given the low complexity (one boolean), it is mostly adequate. However, it does not describe the expected output format or return values, and with no output schema or annotations available, the agent may remain uncertain about how to interpret the results.

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 only lists a boolean 'deep' with no description, and schema description coverage is 0%. The description compensates fully by explaining that deep controls whether to perform a deeper check involving actual API calls to verify visual abilities. This unambiguously clarifies the parameter's purpose.

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 explicitly states it checks the availability of a specific list of components (oMLX, VLM, MinerU, PaddleOCR, etc.), which satisfies 'specific verb+resource'. This clearly distinguishes health_check from sibling tools that focus on GUI observation, vision inspection, parsing, transcription, and actions.

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 does not mention pre-flight validation scenarios or exclude cases where a deep check is unnecessary. The only hint is the 'deep' parameter explanation, which implies deeper verification but does not offer usage context.

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?

Annotations are absent, so the description bears the full burden of behavioral disclosure. It lists the pipeline steps (frame extraction, ASR, VLM) but fails to mention computational cost, processing time, potential errors, or whether the video file is modified. The read-only nature is implied but not explicit.

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: a one-sentence summary followed by a parameter list. There is no fluff or redundancy beyond repeating parameter names from the schema, but the added Chinese annotations earn their place. The main functionality is front-loaded.

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?

An output schema exists, so return value details are covered. The description explains the processing pipeline and all parameters at a basic level, but it omits important contextual details such as supported video formats, resource requirements, failure modes, or performance expectations. It is adequate for a basic invocation but not for robust selection and planning.

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 0%, so the description must compensate. It does add Chinese labels to all six parameters, which clarifies their meaning. However, the labels are terse; for example, 'task' is just 'analysis task description' with no details on expected task formats or examples, and the relationship between fps and max_frames is left ambiguous.

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 composite function: frame extraction, ASR transcription, VLM visual understanding, and timeline output. This distinguishes it from sibling tools like audio_transcribe or vision_inspect by explicitly combining multiple modalities, though it doesn't name those alternatives.

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?

No guidance is provided on when to use this tool versus alternatives such as audio_transcribe for speech-only tasks or vision_inspect for image analysis. The description assumes the user already knows the appropriate context, offering no exclusions or prerequisite conditions.

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 of behavioral disclosure. It accurately describes the multi-step process (crop, enlarge, re-analyze) and the intended use case (verifying small text, button states). It does not mention potential failure modes, authentication, or rate limits, but for a read-only analysis tool, the core behavior is transparent and aligns with what the tool does.

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 well-structured: a concise opening sentence explaining the core action, a usage guideline sentence, a clear 'Do NOT use' sentence with alternatives, and a tidy list of parameters. It is appropriately sized with no filler or redundant text, and every sentence serves a purpose.

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 tool's complexity (7 params, no annotations, no schema descriptions), the description covers all essential aspects: what it does, when to use it, what inputs are needed and their formats, and how it relates to sibling tools. The output schema exists, so the description need not detail return values. This is effectively a complete guide 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.

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

The schema description coverage is 0%, so the description must fully compensate. It provides a separate Args section explaining every parameter, including serialization details ('bbox: Crop region [x1, y1, x2, y2] in original image pixel coordinates'), format choices ('image_source: local file path or remote URL... auto-detects format'), and backward-compatibility notes. This adds meaning far beyond the raw schema types.

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: 'Crop a region of an image, enlarge it, and re-analyze with OCR/VLM for verification.' It identifies a specific verb ('crop', 'enlarge', 're-analyze') and a resource (image region) and distinguishes itself from siblings by explicitly naming vision_inspect and vision_diff as alternatives for different tasks.

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?

Provides explicit when-to-use guidance: 'Use this tool ONLY when you need to zoom into and verify a specific region of an image.' It also gives clear exclusions with alternatives: 'Do NOT use for: full image analysis (use vision_inspect), comparing two images (use vision_diff).' This leaves no ambiguity about when to select 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.

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

With no annotations provided, the description carries the full burden. It does disclose that the tool compares images and can produce pixel-level diffs (via include_pixel_diff), but it does not mention whether the tool is read-only, handles remote/local sources differently, or any potential side effects. Some behavioral context is present, but significant gaps remain.

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 well-structured: a clear purpose sentence, explicit usage rules, then a compact arg list. Each line earns its place, and the layout makes it easy to scan. No redundancy or fluff.

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 tool's complexity (8 params, no schema descriptions, no annotations) and the existence of an output schema, the description covers purpose, usage, and parameter semantics. It omits details like error handling or return format, but the output schema likely covers that. Minor gaps in edge-case behavior prevent a perfect score.

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 0%, so the description must compensate, and it does thoroughly. It explains all 8 parameters, including the relationships between source, path, and data variants, and flags backward compatibility. This is far more useful than the bare 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 opens with a specific verb and resource: 'Compare two UI screenshots or a design mockup with an implementation screenshot to identify visual differences.' It clearly distinguishes this tool from siblings like vision_inspect, which is called out as the alternative for single-image 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 explicitly states when to use: 'Use this tool ONLY when comparing an expected/reference UI with an actual implementation.' It also lists exclusions and alternatives: 'Do NOT use for: analyzing a single image (use vision_inspect), error diagnosis, general image comparison.' This is exemplary usage guidance.

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, the description carries the full burden. It discloses auto-detection of input formats via image_source, lists backward compatibility parameters, and explains the mode options. However, it does not mention side effects, error behavior, or safety profile (e.g., read-only nature), which would be relevant for a tool that processes user-provided images. Still, it adds meaningful behavioral context beyond the schema.

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 well-structured, front-loaded with the core purpose, followed by usage exclusions, input format guidelines, and an Args list. Every sentence serves a purpose, and the bullet-like format makes it easy to scan. Despite covering 9 parameters, it remains compact and free of fluff.

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 tool's complexity (9 parameters, 0% schema coverage, no annotations), the description provides near-complete context: it covers all parameters, explains the recommended input source, lists mode values, and gives clear sibling distinctions. An output schema exists, so not explaining return values is acceptable. No major gaps remain.

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 0%, so the description must compensate. It does so thoroughly: every parameter is listed in the Args section with a concise explanation, and image_source gets extra detail with concrete format examples (local path, URL, data URI, plain base64). This adds substantial meaning beyond the bare schema titles.

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 starts with a specific verb and resource: 'Analyze a single image' and lists concrete use cases (screenshot understanding, UI analysis, chart comprehension, error extraction). It explicitly distinguishes from siblings by naming vision_diff and vision_crop_verify as alternatives for excluded tasks, 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.

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

The description states clearly when to use ('Use this tool ONLY when the user has an image and wants to understand its content') and when not to use it, naming the alternative tools for two specific excluded scenarios. This provides explicit usage context and differentiation from siblings.

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