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

With no annotations, the description covers key behavioral traits: it consumes AI compute, has per-project limits for non-subscribers, and takes 35-130 seconds. It implies results are saved to the project, which is a side effect. No contradictions.

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, with three sentences each adding value: purpose, output location, and constraints. No redundant words, and the most important information (what it does) is first.

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 no output schema, the description could specify the format of results, but it states results are saved to the project, which may be sufficient. The constraints and parameters are well-documented. Minor gap about error cases or prerequisites (e.g., need authenticated user?), but overall complete for a focused 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 input schema already describes all three parameters (project_id, share_text, analyze_structure) with 100% coverage. The description adds minimal extra meaning beyond the schema, just confirming that share_text is the link and that structure analysis is optional. 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 analyzes Douyin videos by extracting oral copywriting and viral structure analysis. It specifies the input (share link) and output (results saved to project), distinguishing it from sibling tools focused on rendering and uploads.

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 for when to use (have a Douyin share link, need analysis) and includes constraints (non-subscription limit, time cost). However, it does not explicitly mention when not to use or suggest alternatives, but no direct sibling exists for this task.

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, but the description explains the authentication flow: checks key, opens login page if needed, redirects to a configurable base URL, and saves key on success. It does not mention error cases or side effects, but for a zero-parameter tool it is fairly transparent.

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 paragraph that efficiently covers purpose and usage details. It could be slightly more concise, but it is well-structured and 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 explains the authentication process but does not mention return values or outputs. Since there is no output schema, the description should describe what the tool returns (e.g., success, token, error). This gap lowers completeness.

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 no parameters, and schema coverage is 100%. The description adds no parameter details, but none are needed. Baseline score of 4 applies.

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 authenticates by checking API key or opening a local login page. It details the process, distinguishing it from sibling tools like video rendering or template listing.

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 the tool should be used before other operations and provides setup instructions for API key configuration. It doesn't explicitly state when not to use it, but the context is 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?

Without annotations, the description fully discloses key behaviors: how narration vs silence holds work, actual audio length measurement for narration, pure silence duration recommendations, total time limit of 10 minutes, and strict requirements for afterChar and page_marks. It effectively communicates what the tool does under different conditions.

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, using a single paragraph that delivers essential information without redundancy. It is front-loaded with the main purpose and follows with details. While it could benefit from bullet points for readability, the current structure effectively conveys all needed information in a compact form.

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 complexity of 8 parameters and no output schema, the description is remarkably complete. It covers all necessary aspects: purpose, parameter usage, constraints, prerequisites (e.g., page_marks for multi-page), and a critical call-to-action (call get_render_preview before rendering). No gaps remain 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?

Although the schema covers 100% of parameters with descriptions, the tool description adds significant value by explaining relationships among parameters (e.g., page_marks must align with script, afterChar must match charEnd, narration triggers separate TTS). It provides context that the schema alone does not, such as durationMs ranges and the 10-minute limit, enhancing the agent's understanding.

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: configuring dubbing, script, and audio-visual synchronization with optional holds. It uses specific verbs and resources (设置配音配置、解说文案、声画同步) and distinguishes it from sibling tools like get_render_preview or upload_html, which serve different functions.

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, including prerequisites (project_id, script, voice_model), constraints (afterChar must equal charEnd, page_marks must cover script), and recommendations (durationMs range, total TTS+holds limit). It also mentions when not to use it implicitly by requiring page_marks for multi-page and calling get_render_preview before rendering. No explicit alternative is needed as sibling tools have distinct purposes.

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?

Discloses side effect of triggering membership/trial check and that projectId is reusable. No annotations provided, so description serves as main transparency source.

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?

Three concise sentences, front-loaded with core action and output, followed by context and side effect. No wasted 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 creation tool with one parameter and no output schema, description fully covers behavior, output, workflow integration, and side effects.

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 covers 100% of parameters with description for 'title'. Description adds no additional parameter meaning beyond 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?

Description clearly states 'create a new video project' and returns projectId. Distinguishes from siblings that operate on existing projects.

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?

Implied that this tool should be used first to obtain projectId for subsequent operations, but no explicit when-to-use or alternatives 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?

No annotations provided, so description carries full burden. It states it's a read operation ('读取') and 'no upload needed', implying no side effects. However, does not disclose auth requirements or return format, leaving some behavioral uncertainty.

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?

Single sentence packs purpose, scope, and usage timing without redundancy. Front-loaded with key action '读取' and ends with pragmatic when-to-call. No wasted 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?

Given zero parameters and no output schema, the description tells the agent what it does and when to call. Could mention the return format, but for a read-only guidelines tool, it is adequate and fits the workflow context.

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?

Zero parameters, so baseline 4 per rules. Description adds meaning by explaining what conventions are read (duration, pageMarks, audio), which is useful beyond the empty 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 reads platform conventions for material duration, pageMarks, and video original sound when embedding HTML. It distinguishes from siblings that perform actions like upload, render, or analyze.

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?

Explicitly says 'should be called before generating HTML/dividing pageMarks', providing clear when-to-use guidance. Lacks explicit exclusions or alternatives, but context with siblings implies this is a preparatory step.

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 provided, so description carries full burden. It describes the tool as fetching a summary and returning a read-only preview URL, disclosing its non-destructive nature. Adds context about user confirmation step. Could mention if return is just URL or includes other data, but sufficient for a read-only preview.

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?

Two sentences: first defines purpose, second provides workflow instructions. Every sentence is essential, no redundant words. Efficiently structured.

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 simple tool (1 param, no output schema), description covers purpose, usage, and transparency. Lacks explicit mention of return value structure (e.g., object with previewUrl field), but for a preview tool this is minor. Still, it provides enough context for an AI agent to use 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 100% (one parameter with description). Description adds context that it fetches '当前项目的 HTML 与配音文案等摘要' but does not add new meaning beyond the schema. 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?

Description clearly states the verb '拉取' (fetch) and resource '当前项目的 HTML 与配音文案等摘要' (current project's HTML and dubbing script summary), returning a '本机只读预览页 URL'. This distinguishes it from siblings like render_video (which renders) and get_render_status (which checks status).

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?

Explicitly states '渲染前必须' (must before rendering) and instructs to have user check previewUrl in browser, then pass user_confirmed_content: true to render_video only after verbal confirmation. Provides clear when-to-use and how-to-use with sibling render_video.

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 key behaviors: returns progress during rendering and video link after completion. It does not cover error states, but for a simple status check this is sufficient.

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?

Two concise sentences in Chinese, front-loaded with purpose, no wasted 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?

Given a single parameter and no output schema, the description adequately covers return states and polling guidance. It is sufficient for basic usage, though could mention failure modes.

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 100% with parameter description '项目 ID'. The description does not add additional meaning beyond the schema, so baseline score of 3 applies.

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: '查询渲染状态' (query render status) and specifies what it returns in different states. However, it does not explicitly distinguish from sibling tools like render_video or get_render_preview.

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 advises polling every 15 seconds, providing a usage guideline. But it lacks details on when to stop polling, prerequisites, or alternatives.

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 must carry the full burden. It mentions the tool is optional and retrieves details, but does not explicitly state read-only behavior, authentication needs, or side effects. The purpose implies a read operation, but more clarity on behavior would improve this score.

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 efficiently conveys purpose, usage context, and optionality without extraneous 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?

Given the tool has a single parameter and no output schema, the description adequately covers purpose and usage. It specifies the return concept ('规范与示例'), though it does not detail the structure. This is sufficient for a simple retrieval 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 100% (template_id described as '模板 ID'). The overall description adds no extra meaning beyond the schema, meeting the baseline for full coverage.

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 retrieves template specifications and examples, and indicates it is optional and only for HTML generation. It distinguishes from siblings like list_templates by specifying a conditional use case.

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?

Explicitly states when to call ('only when user wants to generate HTML based on a template') and that it is not a necessary step. Does not mention alternatives or when not to use, but the context of optionality provides sufficient 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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states 'list', implying read-only, but does not explicitly confirm no side effects, required permissions, or rate limits. Minimal transparency beyond the action verb.

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?

Two sentences efficiently convey purpose, optionality, and alternative approach. No filler words; information 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?

Lacks output format details (e.g., array of template objects) since no output schema exists. However, for a parameterless list tool, the description covers the essential use case. Could be more complete by mentioning what the return data looks like.

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?

Input schema has zero parameters, so schema description coverage is 100%. The description adds context by specifying the type of templates (HTML video) and their role as reference layouts, which is helpful beyond the empty 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 lists built-in HTML video templates for reference layout use. It also contrasts with the alternative of not using templates, and implicitly distinguishes from get_template_detail which provides details of a single template.

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?

Explicitly states when to use (when a reference layout is needed) and when not to (users can provide their own HTML). It could be improved by explicitly naming alternatives like get_template_detail or direct HTML upload, but the guidance is 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 must cover behavioral traits. It does not mention that the tool is read-only, has no side effects, or other behavioral details, leaving the agent uninformed.

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?

Two sentences with no wasted words. The first sentence states the purpose and output fields, the second adds context about AI matching. Efficiently 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?

For a simple parameterless listing tool, the description is complete. It covers what is returned and why it matters, despite no output schema. Sibling tools like configure_voice_and_script provide context for usage flow.

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 0 parameters and 100% schema coverage, yet the description adds value by listing the specific metadata fields returned (id, name, gender, trait, description, tags, suggestedFor), which the schema does not detail.

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 '返回所有可用配音音色' (returns all available dubbing voices), specifying the verb and resource. It lists metadata fields (id, name, gender, etc.), distinguishing it from siblings like configure_voice_and_script.

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 says AI uses the output to automatically match voice to content tone, implying when to use this tool (for voice selection). However, it does not explicitly state when not to use it or mention alternatives.

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 provided, so description carries full burden. It discloses the 2-10 minute duration and that user confirmation is required, but does not mention whether it is destructive, rate limits, or side effects. It returns a progressUrl, which is helpful but lacks detail on the output structure.

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?

Two well-structured sentences with no fluff. Front-loaded with core action and timing, then prerequisite and output. Every word is useful.

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 complex, long-running tool with no output schema, the description is remarkably complete: it explains the process, time estimate, prerequisite step, required parameter condition, and what the response contains. Sufficient for the agent to use 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 coverage is 100% so baseline is 3. The description adds value by explaining that user_confirmed_content must be true because the user already reviewed the HTML and dubbing script. Aspect_ratio default is already in 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 that the tool triggers video rendering involving TTS, screen recording, and mixing, with a duration of 2-10 minutes. It specifies the prerequisite of get_render_preview and user confirmation, distinguishing it from sibling tools like re_render_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?

Explicitly states that get_render_preview must be called first and user_confirmed_content must be true. This provides clear when-to-use and prerequisite guidance, ensuring correct invocation.

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?

Discloses quota deduction and rendering lock, but lacks details on success/failure responses. Since no annotations, description carries burden and does well.

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?

Concise Chinese description with no wasted words. Front-loaded with core action and quota impact.

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?

Covers main behavioral constraints and usage context. Lacks output schema but described effects adequately for a simple 3-param 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 coverage is 100%, so baseline 3. Description repeats schema info for user_confirmed_content but adds no new meaning beyond 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?

Clearly states force re-render video with quota deduction, and specifies when to use (after modifications or dissatisfaction). Differentiates from sibling render_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?

Explicitly says when to use (after changes or dissatisfaction), when not to use (while rendering), and requires user confirmation before calling.

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 the tool returns specific outputs (slide count, summaries, warnings) but does not elaborate on side effects, authorization needs, or whether it modifies existing data. The description is adequate but not exhaustive.

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, efficiently front-loading the purpose and then the return values. Every sentence 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?

Given the tool's moderate complexity and no output schema, the description adequately explains both input modes and return values. It covers essential details for an agent to use the tool correctly. Minor improvement could be mentioning whether it creates or replaces content.

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 100%, so parameters are already documented. The description adds the nuance that 'html_content' and 'html_file' are mutually exclusive, which is helpful but not a major improvement over the schema. 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 uploads HTML content to a project, supporting two input modes (string or file path), and specifies the return values (slide count, summaries, warnings). This distinguishes it from sibling tools like 'upload_material' which likely handles other media types.

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 does not provide explicit guidance on when to use this tool versus alternatives. It implies usage via the tool's name and description of input options, but lacks exclusion criteria or context for choosing between upload methods or other sibling tools.

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?

Discloses video transcoding to H.264 MP4, return fields, and a specific instruction (do not write FFmpeg overlay). With no annotations, it covers key behavioral traits adequately.

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?

Single paragraph that front-loads purpose and returns, then provides behavioral details. Concise but could be better structured with bullet points.

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?

With no output schema, the description lists return fields and usage tips. It references a sibling tool for additional constraints. Moderately complete, missing error handling but sufficient for common 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?

Schema already describes both parameters (100% coverage). The description does not add significant meaning beyond the schema; it only provides general context about the upload process.

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 uploads images or videos to OSS and lists the return values. It distinguishes from sibling 'upload_html' by specifying different resource types.

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 recommendations (video length 5-15s, hard cap 10min) and directs to get_material_guidelines for size limits. Does not explicitly specify when not to use this tool, but context is clear.

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