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

Annotations already declare read-only and idempotent behavior. The description adds meaningful context about the return format (Markdown scene summary), the uniform frame extraction behavior, and the default to include audio transcription, which goes beyond basic safety annotations. No contradiction found.

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: one-sentence summary followed by a structured list of arguments and return value. Every sentence and field adds value, with no redundancy 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?

Given the tool's complexity and the schema lacking param descriptions, the description covers all parameters, return format, and core behavior. It does not mention time/resource limitations (e.g., video size limits), but annotations cover safety aspects, so the overall context 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?

Schema description coverage is 0%, but the Args section fully documents each parameter: video_path (local absolute path, supported formats), max_frames (range 1-20, default 6), include_audio (default true), and question (optional focus). This completely compensates for the missing schema 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?

Description clearly states it extracts frames from video and optionally transcribes audio, distinguishing it from sibling tools like mm_describe_image (single image) and mm_transcribe_audio (audio-only). The verb '分析视频' (analyze video) with specific resources and capabilities makes 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.

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

Usage context is implied: it's for video analysis with frame extraction and optional audio transcription. However, it does not explicitly mention when to use this tool instead of alternatives (e.g., audio-only tasks should use mm_transcribe_audio), nor does it mention exclusions or prerequisites.

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 already provide readOnlyHint=false and destructiveHint=false, and the description adds meaningful context: supported file formats (.txt/.md with UTF-8/GBK), parameter ranges (max_scenes 1-50), and that the output is an editable JSON script. It does not contradict annotations and clarifies the tool's generative, non-destructive nature.

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 with a clear opening purpose, an Args section, and a Returns section. Every sentence provides useful information without redundancy, making it efficient and easy to scan.

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 (novel-to-script generation), the description covers all key aspects: inputs, parameter constraints, output format, and editability. It lacks details on potential errors, processing time, or side effects, but these are adequately implied by annotations and the presence of an output schema.

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?

Despite 0% schema description coverage, the description fully documents each parameter: novel_path (absolute path with supported extensions and encodings), style (default 日系动漫), and max_scenes (range and default). This adds significant meaning beyond the schema's bare types and defaults.

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 with a specific verb and resource: '上传一部小说，自动生成漫剧剧本 JSON' (upload a novel, auto-generate comic script JSON), and specifies the output includes character cards and storyboards. This distinguishes it from siblings like mm_generate_image or mm_start_comic_video, which handle different media generation stages.

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 context (adapting a novel into a script for comic video production) but does not explicitly state when to use this tool versus alternatives like mm_generate_image or mm_start_comic_video. There are no explicit exclusions or alternative references, so the guidance remains implied rather than direct.

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 already cover read-only safety (readOnlyHint, idempotentHint, destructiveHint). The description adds valuable behavioral context beyond annotations, such as input format restrictions and the return type (Markdown text), which is useful for the agent.

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 with clear sections (summary, Args, Returns). Every sentence adds value, and the main purpose is front-loaded, making it easy for the agent to parse.

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 low complexity (2 simple params) and existing output schema, the description is complete: it includes purpose, parameter semantics, return type, and input constraints. No critical information is missing for correct 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 0%, making the description's Args section essential. It explains image_path with absolute path and supported formats, and prompt as optional with a concrete example, fully compensating for the lack of schema 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 the tool analyzes local images and returns text descriptions, using a specific verb+resource+output structure. It distinguishes itself from sibling tools by specifying 'image' as the media type, differentiating from audio/video 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 provides clear context on when to use the tool by specifying it works with local image paths and supported formats (PNG/JPEG/WebP/GIF). It implies exclusions (e.g., remote URLs, unsupported formats) but does not explicitly name alternatives or when-not-to-use 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?

The description adds useful behavioral details beyond annotations: it specifies saving to output_path (defaulting to outputs/images/), lists supported sizes, and returns an absolute path. It aligns with readOnlyHint=false 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.

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

The description is concise and well-structured: a one-sentence summary followed by Args and Returns sections. No unnecessary information 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?

The description covers all parameters, defaults, and the return type, which is sufficient for a simple image-generation tool. It could mention error behavior or file-overwrite details, but these are not critical 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?

With 0% schema description coverage, the description fully explains each parameter: prompt (image content), size (supported formats), and output_path (optional, default). This provides necessary meaning beyond the raw 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 generates and saves an image from a text prompt, distinguishing it from sibling tools like mm_generate_video and mm_describe_image.

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?

Usage is implied from the purpose, but there is no explicit guidance on when to use this tool versus alternatives, nor any exclusions or 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?

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses that the operation is asynchronous, returns a task ID, takes several minutes, and requires polling via mm_query_video_task. This provides rich behavioral context that annotations alone do not cover.

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 with a one-line summary, a clear Args list, and a Returns note. Every element earns its place, and there is no redundant or filler content.

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 tool with 5 parameters, async behavior, and a follow-up workflow, the description covers inputs, return value, and next steps. It even specifies the likely return type (task ID) and generation time, making it a complete standalone reference.

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 has no property descriptions (0% coverage), but the description's Args section gives detailed semantics for all 5 parameters, including constraints (prompt max 512 chars, duration choices 5/10, allowed resolutions, fps choices 30/60, with_audio default false). This fully compensates for the schema gap.

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 it submits an asynchronous video generation task and returns a task ID for polling with mm_query_video_task. It uses a specific verb ('提交' / submit) and resource (video generation), and distinguishes from sibling tools that handle other media or query 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?

It explicitly explains the asynchronous workflow and directs the user to mm_query_video_task for querying results, giving clear follow-up guidance. However, it does not explicitly contrast with alternative generation tools like mm_generate_image, so the when-not-to-use aspect 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.

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds return behavior (progress vs. final path), but since an output schema exists, this is partially redundant. No contradiction 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.

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

The description is concise with three clear sections: purpose, Args, and Returns. Every sentence earns its place, and the front-loaded purpose sentence immediately conveys what the tool does. No unnecessary words.

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 simple query tool with one parameter and an output schema, the description adequately covers the operation, input origin, and return type. It could mention explicit alternatives or when not to use, but the context signals (sibling tools) and naming make the specialization clear.

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 0%, but the description compensates by explaining that job_id is the ID returned by mm_start_comic_video. This adds meaningful semantics beyond the schema's bare 'Job Id' field, though more detail about format or constraints could be provided.

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: querying comic production task progress and returning the final video path upon completion. The verb '查询' and resource '漫剧生产任务进度' are specific, and the reference to mm_start_comic_video distinguishes it from the generic sibling mm_query_video_task.

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 explains that job_id comes from mm_start_comic_video, providing clear context for when to use this tool (after starting a comic video task). It does not explicitly list alternatives or exclusions, but the context is sufficient for a focused query tool.

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?

The description discloses important side effects (downloading MP4 to local) and return behavior for both in-progress and success states, going beyond what annotations alone provide. It also mentions a default output path, adding useful context.

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, starting with a clear summary followed by Args and Returns sections. Every sentence serves a purpose without 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?

For a simple 2-parameter tool, the description covers the essentials: purpose, parameter semantics, and return value behavior. It lacks detailed error handling or explicit alternative exclusions, but the provided info is sufficient for normal agent use.

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?

Despite 0% schema coverage, the description explains both parameters thoroughly: task_id comes from mm_generate_video control flow, and output_path has a default with optional saving. This fully compensates for the bare input 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 queries a video generation task and downloads the MP4 file after success, using a task ID from mm_generate_video. This specificity differentiates it from siblings like mm_query_comic_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 explicitly ties task_id to mm_generate_video, giving clear context on when to use this tool. It doesn't explicitly exclude alternatives, but the source of the task ID and the tool's name make its purpose clear enough for an agent.

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?

The description discloses that the task runs in the background and generates shots sequentially, which is behavioral context beyond the annotations. It also explains that it returns a job_id for later status queries and that resume_job_id can resume unfinished jobs. These details complement the annotations' readOnlyHint=false and openWorldHint=true 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.

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

The description is compact and well-structured: a one-sentence summary, followed by a clean Args list and a Returns line that points to the query tool. Each line adds value without 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 description covers the core workflow: input, options, output, and follow-up. It mentions the return type and the sibling tool for querying, and the background behavior. For a tool that starts an async job, this is sufficient context for an agent to select and invoke it 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 provides a full Args section with detailed explanations for all three parameters, including default values, trade-offs (fast vs slow size), and the origin of script_path (generated by mm_create_comic_script). Since the schema has 0% description coverage, this completely fills the gap.

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 '启动' (start) with a clear resource '漫剧生产任务' and specifies the input (script JSON) and mode (background shot-by-shot). This distinguishes it from sibling tools like mm_create_comic_script (which creates the script) and mm_query_comic_video (which queries progress).

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 clearly states the prerequisite (script JSON from mm_create_comic_script) and points the user to mm_query_comic_video for progress, establishing the tool's position in the workflow. It also explains resume_job_id for continuing incomplete jobs, providing context on when to resume. However, it doesn't explicitly mention when not to use this versus mm_generate_video, so it's not a full alternative comparison.

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 indicate non-read-only and non-destructive behavior. The description adds that the tool saves to MP3 and returns an absolute path, which gives concrete side-effect information beyond the annotations. It does not contradict annotations and offers useful 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.

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

The description is a well-structured docstring with a concise purpose statement followed by Args and Returns sections. Every element serves a purpose, with no unnecessary wording. It is front-loaded with the core functionality.

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 essential input parameters, defaults, and return type, making it sufficient for a simple TTS tool. Minor gaps remain, such as overwrite behavior and a list of supported voices, but the description is largely complete for typical use.

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?

With 0% schema description coverage, the description compensates by explaining each parameter: text (max 1000 chars), voice (default zh-CN-XiaoxiaoNeural), and output_path (default outputs/audio/). This adds practical meaning, though it leaves some ambiguity about whether output_path is a directory or full file path.

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: '把文字合成为语音并保存为 MP3' (synthesize text into speech and save as MP3). This specifies a distinct action (synthesis) and output format, distinguishing it from sibling tools like mm_transcribe_audio (inverse task) and mm_generate_image/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 practical constraints (max 1000 characters) and defaults (voice, output path), which imply when to use the tool. However, it does not explicitly mention alternatives or when not to use it, leaving usage guidance 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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: it requires a local absolute path (not a URL), supports specific formats, defaults language auto-detection, and returns a Markdown structure with language, full text, and segments. This goes beyond what annotations provide.

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. The purpose is front-loaded in one sentence, followed by concise Args and Returns sections. Every sentence adds value—no filler, no repetition of the tool name or title.

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 essential aspects for a transcription tool: input format, supported extensions, optional language parameter, and return format. Combined with annotations (read-only, idempotent) and the low parameter count, the description is complete and leaves no major gaps for an agent to misuse the 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?

Schema description coverage is 0%, but the description fully compensates. It explains audio_path requires an absolute local path and lists supported formats. It explains language is optional ISO 639-1 (e.g., zh, en) and defaults to auto-detection. Every parameter is meaningfully described beyond the raw 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 '转写本地音频为文字' (transcribe local audio to text), a specific verb+resource statement. This clearly distinguishes the tool from siblings like mm_synthesize_speech (speech generation) and mm_analyze_video (video analysis), making its 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 implies usage context by specifying 'local audio' and listing supported formats (MP3/WAV/M4A/FLAC/OGG). It does not explicitly name alternatives or exclusion criteria, but the sibling list shows no overlap, so clear context suffices. A stronger statement like 'use this instead of mm_synthesize_speech when transcribing' would earn a 5.

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