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

No annotations provided, so description carries full behavioral disclosure burden. It covers image count limits (1-15), model versions, output formats, watermark, and save_to path. Does not mention auth needs or rate limits, but the generative nature is well-described with continuous sequence. Lacks details on error states or retry 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?

Extremely concise: three sentences plus two examples. Front-loaded with core purpose. No filler; every sentence adds value.

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 8 parameters and no output schema, description covers all aspects: usage scenarios, limits, model choices, output formats, and provides examples. Sufficient for an AI agent to understand tool capabilities and limitations.

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%. Description adds meaning beyond schema: prompt as '描述组图的主题和内容', model as '需 4.5 或 5.0', save_to as 'b64_json 模式必填', etc. Provides examples for prompt. Adequately informs parameter usage.

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?

Clear verb+resource: '组图生成：根据文本描述生成一组连续图片.' Specifies generation of a sequence of continuous images. Distinguishes from siblings like seedream_text_to_image (single image) and seedream_merge_images (merge).

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?

Explicit when to use: '适用于需要生成多张连续画面的场景，如故事板、漫画分镜等.' Also mentions supported models (4.5 and 5.0) and batch limit of 15. Does not explicitly state when not to use or name alternatives, but context implies single-image tasks use text_to_image.

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 states that the tool generates a new image based on a reference and prompt, but it does not disclose behavioral traits such as destructive nature (e.g., whether the original image is modified), authentication requirements, rate limits, or error handling (e.g., invalid URL). The examples are illustrative but not transparent about 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 very concise, with just one sentence and two example prompts. It is front-loaded with the purpose. While efficient, it could be slightly more structured (e.g., bullet points for models or parameters). No redundant information, but the conciseness leaves out useful details.

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 (9 parameters, no output schema), the description is minimal. It covers the core functionality but does not explain output behavior, response formats, or parameter interaction. The schema covers parameter descriptions, so the description's job is to provide higher-level context, which it does only partially. The examples help but are not sufficient for full contextual 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 input schema has 100% description coverage, meaning each parameter is already explained in the schema. The tool description adds minimal additional semantic value beyond the schema: it provides example prompts but does not elaborate on parameter meaning, constraints, or interactions. Thus, a baseline score of 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's purpose: '图生图：基于参考图片生成新图片' (image-to-image: generate a new image based on a reference image). It provides specific examples of prompts, making the intent unmistakable. It is well-distinguished from sibling tools like seedream_text_to_image by explicitly requiring a reference image URL.

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 when to use the tool: provide a reference image URL and a text description. However, it does not provide any guidance on when not to use it or how it compares to alternatives like seedream_text_to_image or seedream_merge_images. The mention of model versions (4.5 and 5.0) is helpful but not sufficient for clear usage boundaries.

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 accurately portrays a read-only listing operation with no side effects, which is sufficient given no annotations are provided.

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, front-loaded sentence with no extraneous words; every word adds value.

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

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

For a zero-parameter, output-schema-less listing tool, the description is fully complete and requires no additional 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?

No parameters exist; the description correctly adds no parameter information (baseline 4).

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 lists available Seedream model versions and their features, using a specific verb-resource pair that distinguishes it from sibling generation 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 context (before generation), but provides no explicit guidance on when to use vs alternatives or exclusion criteria.

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 discloses that the tool generates a new image by merging URLs and a prompt, and that up to 10 images are supported. However, it does not mention any behavioral traits like output resolution constraints, processing time, or whether the original images are modified. Given the lack of annotations, this is adequate but not thorough.

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 extremely concise: a one-line purpose, a short explanation of usage, and two examples. Every sentence adds value, and there is no filler. It is front-loaded with the core 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 moderate complexity (8 parameters, 2 required, no output schema), the description covers the essential aspects: how to use, what parameters are needed, and how to refer to images. It lacks details about the return format or model differences, but the schema already provides parameter descriptions. Overall, it is sufficiently complete for an agent to use the tool effectively.

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 well-documented in the schema. The description adds value by explaining that images can be referenced as '图1' etc. in the prompt and provides examples, but this reinforces rather than significantly extends the schema descriptions. A score of 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 '多图融合：融合多张图片生成新图片' which translates to a specific verb+resource: merging multiple images into a new one. It provides concrete examples and distinguishes this tool from siblings like text_to_image or image_to_image by focusing on multi-image fusion.

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 tells when to use the tool (when you have multiple images to merge) and includes a limit of 10 images. It does not explicitly state when not to use or compare to alternatives, but the context is clear enough that an agent would understand this is for merging, not generation from scratch.

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

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

With no annotations provided, the description carries the full burden. It discloses that multiple images are supported only for certain model versions, and mentions output formats (URL or base64) and watermarks. However, it does not address potential issues like rate limits, content moderation, or timeout, leaving gaps in behavioral knowledge.

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: purpose statement, model capabilities, examples, and a note. The three example prompts, while useful, add some verbosity. Overall, it is largely concise and front-loaded, with minimal waste.

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 8 parameters and no output schema, the description covers critical aspects: model versions, image count, size options, output formats, and watermark. It does not detail the return structure (e.g., how URLs are presented), but for an image generation tool, the provided information is sufficient for basic invocation.

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

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

Schema coverage is 100% (baseline 3). The description adds value by explaining model version constraints for the 'n' parameter, suggesting prompt length limits, and noting that size can be custom (e.g., 1920x1080). This enriches the schema beyond defaults and enums.

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 generates images from text descriptions ('文生图：根据文本描述生成图片'), providing clear purpose. It uses a specific verb ('生成') and resource ('图片'). However, it does not differentiate from sibling tools like seedream_image_to_image or seedream_merge_images, lacking explicit contrast.

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 a useful note on model version limitations for multiple images ('注意：5.0 和 4.0 版本支持 n>1，4.5 仅支持 n=1'), guiding parameter selection. It also provides example prompts to illustrate usage context. No explicit when-not-to-use or alternative tools mentioned, 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?

No annotations are present, so the description carries full burden. It mentions the search-before-generation behavior and model restriction, but fails to disclose potential issues like search failure handling, rate limits, or any destructive aspects. Behavioral traits beyond the core function are lacking.

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 short and front-loaded with the core purpose. Every sentence is meaningful: first sentence states function and model restriction, second explains use case, and examples illustrate. Zero 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 the lack of output schema, the description adequately explains the tool's purpose and use case. It covers model restriction and parameter semantics. However, it could be more complete by describing the output format or what the generated image 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?

Schema coverage is 100%, so parameters are well-documented. The description adds context for the prompt parameter (can include real-time requirements) and reiterates model restriction. However, it adds minimal new semantic value beyond the 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 combines web search with text-to-image generation, specifying it's only for the 5.0 model. The verb 'generate image' and resource 'web search + text' are explicit, and it distinguishes from siblings by model version restriction.

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 (scenarios needing real-time info) and explicitly states it's exclusive to the 5.0 model. Examples are given but it does not explicitly mention when not to use or list alternatives among siblings.

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