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

No annotations are provided, and the description only mentions pricing ($0.02/call, 5 free today). It discloses no behavioral traits such as whether the tool is read-only, destructive, or has rate limits. This is critically 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 extremely concise (one line), which is positive for brevity, but it omits essential information. It lacks structured details such as what the output contains or constraints on input images.

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 simple schema and no output schema, the description should provide thorough context about what the tool returns (e.g., animal species, confidence scores). It fails to do so, leaving the agent without adequate information to assess utility.

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% coverage with a single parameter 'image' described as '动物图片URL'. The description adds no additional meaning beyond the schema, so the 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 includes '[Vision] 动物识别' which clearly indicates this tool recognizes animals from images. However, it does not differentiate from sibling vision tools like baidu_object_detect or baidu_plant, but the name itself is sufficiently specific.

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 guidance on when to use this tool versus alternatives. For example, it does not mention that this tool is for animal recognition specifically or suggest other tools for different object categories.

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 shoulders burden. It does not disclose latency, supported languages, audio format restrictions, or limits beyond the free quota. Minimal behavioral info.

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 line, front-loaded with the key purpose. It includes pricing info, which may be useful, but no extraneous content. Efficient but could be more informative.

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?

No output schema exists, and the description does not mention return format (text, confidence) or error handling. For a simple 1-parameter tool, this is minimally adequate but lacks completeness for an agent.

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%, so the schema already documents the audioUrl parameter. The description adds no extra meaning (e.g., accepted formats, max size). 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 converts voice to text using '[Voice] 语音转文字（ASR）', which is a specific verb+resource. Among sibling tools, no other ASR tool exists, so it distinguishes well.

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 on when to use this tool vs alternatives. The description only mentions pricing and free quota, but no context about usage scenarios or exclusions.

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

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

No annotations are provided, so the description carries the full burden. It reveals pricing and free quota but fails to disclose side effects, data handling, read-only nature, or return behavior. Inadequate for a detection tool.

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

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

Very concise, one sentence plus pricing. However, it mixes purpose and pricing info without clear structure. Could be more formal but still acceptable for a simple tool.

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?

Does not describe the output format, keypoint details, or any response structure. Given no output schema, the agent is left uninformed about what to expect after calling 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?

The schema already describes the image parameter with 100% coverage. The description adds no extra semantics beyond the schema's '人体图片URL' description, 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 detects human body keypoints, distinguishing it from sibling tools for face, gesture, animal, etc. The verb 'detect' and resource 'body keypoints' are specific.

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 on when to use this tool vs alternatives like baidu_gesture or baidu_face_detect. The description only provides functionality and pricing, leaving the agent to infer 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?

No annotations exist, so the description must disclose behavioral traits. It adds cost and quota information ($0.02/call, free 5/5 today), which is helpful. However, it does not explain the output format, what kind of car information is returned, or any limitations, leaving significant gaps.

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, consisting of a single line with key identifiers and cost info. It is front-loaded but lacks elaboration; however, it earns its place without 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?

With one parameter, no output schema, and no description of the return value or behavior, the tool is underspecified for an AI to fully understand its usage. The context signals (siblings, annotations) do not compensate for the lack of 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?

Schema coverage is 100% with the parameter 'image' described as '车辆图片URL'. The tool description adds no additional semantics beyond what the schema already provides, resulting in a baseline score of 3.

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

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

The description clearly indicates this tool is for vehicle recognition under the Vision category, with a specific verb (识别) and resource (车辆). It distinguishes from sibling tools like baidu_vehicle_detect by focusing on identification rather than detection.

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 guidelines are provided on when to use this tool versus alternatives like baidu_vehicle_detect or baidu_object_detect. The description only states the function without context for selection.

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

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

No annotations are present. The description includes pricing and free quota information, which is helpful, but lacks disclosure of behavioral traits such as read/write nature, side effects, or required permissions.

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 includes pricing information, but it is not structured and mixes metadata with purpose. It could be more concise while covering essential 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 presence of many sibling OCR tools, the description fails to explain what makes this tool unique, expected output, or any usage constraints. It is incomplete for effective selection.

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 the baseline is 3. The description adds no additional meaning or constraints beyond what is already in the schema (e.g., image format, prompt 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?

The description indicates it is an OCR tool via '[OCR] DeepSeek-OCR 大模型OCR', but it essentially restates the tool name without specifying the action (e.g., 'extracts text from images'). It does not distinguish it from sibling OCR 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?

No guidance is provided on when to use this tool over alternatives like baidu_ocr or baidu_qianfan_ocr. No context for appropriate use cases.

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. The description only mentions pricing and a free limit, but does not disclose response format, token limits, or any side effects. The behavioral burden is not met.

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 line with an [LLM] prefix, making it front-loaded and concise. However, the Chinese characters may affect readability.

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 LLM tool with no output schema, the description is too sparse. It lacks information on return values, model options, and usage constraints.

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 descriptions for both parameters. The description does not add any additional meaning beyond the schema, so it meets the baseline.

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 '深度思考（DeepSeek-R1 链式推理）' to indicate a deep reasoning LLM tool, distinguishing it from other Baidu tools. The [LLM] tag and pricing add context, but the use of Chinese may reduce clarity for some users.

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 on when to use this tool versus other LLM tools like baidu_llm_chat. The description does not specify context 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, and the description does not disclose behavioral traits such as accuracy, response format, or limitations (e.g., what happens if the image is not a dish). The description is too brief to provide meaningful 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 very short but includes pricing information that could be omitted for clarity. It is not tightly structured; the pricing details may distract from the core purpose. Every sentence should earn its place, and the pricing is less relevant for tool selection.

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 simplicity of the tool (one parameter, no output schema), the description lacks completeness by not stating what the tool returns. An agent would need to know the output format or additional behavior. The description is insufficient for full understanding.

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 fully described). The parameter 'image' has a clear description '菜品图片URL', adding meaning beyond the type. The tool description itself does not add extra parameter context, so 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 '菜品识别' (dish recognition) as the tool's function, using a specific verb and resource. It distinguishes itself from sibling tools by specializing in dish recognition, but the description could be more explicit about the action.

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 on when to use this tool versus alternatives. Only mentions pricing and free call limits, which are not usage guidelines. No exclusion criteria or alternative tools are referenced.

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 full burden for behavioral disclosure. It only states the tool is for NLP embedding and mentions pricing, but does not describe side effects, return values, or operational traits such as rate limits or required permissions.

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 short and front-loaded with the category and tool name. It is efficient but lacks further detail; however, conciseness is not penalized heavily for being minimal when the schema is simple.

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 one required parameter, no output schema, and no annotations, the description should provide more context about when and how to use it. The current description is insufficient for an agent to understand the tool's full behavior or how it differs from similar sibling tools like 'baidu_word_embedding'.

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% coverage for the single parameter 'text', describing it as input text separated by '||'. The description adds no extra meaning beyond the schema, so it meets the baseline for high 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 indicates it's an NLP tool for text vector embedding (Embedding-V1), which specifies the verb and resource. However, it does not differentiate from the sibling tool 'baidu_word_embedding', which likely serves a similar purpose.

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 or when not to use it. The pricing info ($0.01/call, free quota) hints at cost, but there is no explicit context for usage decisions.

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?

没有提供任何行为信息，如返回相似度分数、是否需要检测到人脸、图像要求等，且没有注释来补充。

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?

内容非常简短，包含类别和定价，但缺乏核心功能描述，过于省略，没有有效传达工具用途。

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?

对于一个人脸比较工具，没有输出schema，且描述完全未提及输出结果、行为或限制，无法帮助智能体理解其完整功能。

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?

参数schema覆盖100%，描述了图片URL，但描述没有在schema基础上增加额外含义，只提供了无关的定价信息。

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?

描述中包含类别标签[Face]和中文名称'人脸对比'，暗示了比较人脸的功能，但未明确说明是比对两张人脸图像，且与兄弟工具如baidu_face_detect没有区分。

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?

描述只提供了定价信息，没有说明何时使用该工具、前提条件或替代方案，缺乏使用指导。

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 exist, so the description should disclose behavioral traits. It mentions pricing and free quota but omits details like whether the tool is read-only, what image properties are required (e.g., minimum face size), or any rate limits beyond the free tier.

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 short, one line with no fluff. It is front-loaded with the tool's purpose. However, it omits important details that could be included without excessive length.

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 1 parameter, no output schema, and no annotations, the description is insufficient. It does not explain what the tool returns (e.g., face locations, confidence scores), leaving the agent uninformed about the response structure. It also fails to differentiate usage among many similar siblings.

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% (parameter 'image' has description '人脸图片URL'). The description adds no further meaning to the parameter, 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 '人脸检测' (face detection), indicating the tool detects faces in images. This distinguishes it from siblings like baidu_face_compare which compares faces. However, it doesn't specify the output (e.g., bounding boxes, landmarks), lacking full scope.

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 guidelines are provided on when to use this tool versus alternatives like baidu_object_detect or baidu_face_compare. There is no context about prerequisites or typical use cases, leaving the agent to guess.

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, and the description only mentions pricing. It does not disclose behavioral traits such as whether the tool is read-only, any side effects, or what permissions are needed. The agent lacks information about the tool's operational 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 extremely concise: a single line with category tag, name, and pricing. It is front-loaded and efficient, but the brevity comes at the expense of essential details, which is acceptable given the simplicity of the tool.

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 only one parameter, no output schema, and no annotations, the description should provide more context about what the tool returns or how to interpret results. The current description is incomplete for an agent to confidently use the tool without additional assumptions.

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

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

The schema has 100% coverage for the single parameter 'image', describing it as '手势图片URL'. The tool description adds no additional meaning beyond this, so the score is at baseline.

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 states '手势识别' (gesture recognition) and the input schema expects an image URL, making it clear the tool recognizes gestures from images. However, it lacks a verb like 'Recognize' and does not specify what output to expect, which could reduce clarity about the specific 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 provides no guidance on when to use this tool versus sibling tools like baidu_object_detect or baidu_face_detect. It only includes pricing information, which does not help the agent decide contextually.

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 only mentions pricing and free quota, but fails to disclose behavioral traits such as output format, supported sequence lengths, or any potential errors. This is insufficient for a prediction tool.

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

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

The description is very short and fits in one line, which is concise. However, it lacks structure and omits important details like the input format or output type. The brevity sacrifices completeness.

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 no output schema and no annotations, the description should provide enough context for an agent to use it correctly. It only gives the purpose and cost, missing essential details such as expected input format, output, and error handling. This leaves the agent underinformed.

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% coverage with a description for the single parameter 'sequence' as '蛋白质序列'. The tool description adds no additional meaning beyond what the schema already provides, so 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 'HelixFold3 蛋白质结构预测' (HelixFold3 protein structure prediction), which explains the tool's purpose. It distinguishes itself from the many sibling tools that focus on image, audio, or text tasks. However, it uses a noun phrase rather than a verb, which slightly reduces clarity.

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 guidance on when to use this tool versus alternatives. There is no mention of prerequisites, limitations, or comparison with other protein prediction tools. The agent is left without context for appropriate 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?

No annotations provided, and the description only mentions OCR and cost. It does not disclose image requirements, accuracy, or privacy implications, which is important for ID card processing.

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?

Very concise with a single line. Includes useful pricing info, but could benefit from structured format.

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 schema and behavioral details. For a simple OCR tool, it misses context on return format and requirements.

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 of 'image' as URL. The description adds no extra semantics beyond the schema.

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

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

The description clearly states 'OCR ID card recognition' and includes a pricing hint. However, it does not elaborate on the specific type of ID card or distinguish from sibling OCR tools beyond the tag.

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 on when to use this tool vs other OCR tools like baidu_ocr or baidu_ocr_accurate. The agent is left to infer from the name and description.

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, and the description offers no behavioral information. It does not disclose side effects, required permissions, return format, or any constraints. The pricing note is not behavioral.

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 but at the cost of clarity. It includes pricing which is useful but lacks essential operational details. Conciseness should not sacrifice completeness; this is underspecified.

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?

Without output schema or behavioral details, the description is severely incomplete for an image editing tool. The agent has no information about the result (e.g., URL of edited image, failure modes) or workflow requirements.

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 descriptions for both parameters ('原图URL' and '编辑指令'). However, the tool description adds no additional meaning beyond the schema. Baseline score of 3 is appropriate per guidelines.

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 states 'AI图片编辑' which conveys image editing, but it is essentially a restatement of the tool name. It adds the model name 'Qwen-Image-Edit' and pricing, but does not specify the scope of editing operations, leaving ambiguity compared to sibling tools like image generation or enhancement.

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 usage guidance is provided. There is no mention of when to use this tool versus alternatives (e.g., baidu_image_gen, baidu_image_enhance). The agent must infer context from the name alone, which is insufficient.

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 must disclose all behavioral aspects. It mentions pricing and free call limits, which is useful, but fails to explain whether the enhancement is synchronous, what happens to the image (e.g., return a new URL), or any authorization requirements. Given the lack of annotations, this is insufficient.

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

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

The description is a single, front-loaded sentence that conveys the core purpose, category, and cost. It is efficient and easy to parse, though it sacrifices detail for brevity.

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 one-parameter tool, the description covers the basic purpose and cost. However, it omits details such as supported image formats, size limits, output format, and whether the enhancement is automatic or configurable. With no output schema, the agent needs more context on return values.

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

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

The schema has 100% description coverage for the single parameter 'image' (description: '图片URL'). The description adds pricing context but no additional parameter meaning. Per guidelines, with high schema coverage, baseline is 3.

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

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

The description clearly indicates the tool enhances image clarity ('图像清晰度增强'), with an '[Image]' category prefix differentiating it from non-image tools. However, it lacks specificity on the type of enhancement (e.g., denoising, upscaling) and does not explicitly distinguish it from sibling image tools like baidu_image_edit.

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 guidance on when to use this tool versus alternatives such as baidu_image_edit or baidu_image_recognition. There is no mention of use cases, prerequisites, or when not to use it.

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 only discloses the cost ($0.05/call) and free usage count (5/5 today), but lacks behavioral details such as that the tool generates images from text prompts, aspects of the generation process, or limitations. With no annotations, the description should cover more behavioral aspects.

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, consisting of a single phrase and pricing info. It is front-loaded with the purpose. However, the pricing might be considered metadata rather than behavioral guidance. Overall, 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?

Given the simple tool (2 parameters, no output schema, no annotations), the description is incomplete. It does not explain the return format, how the generation works, or any usage notes. The agent would need to infer from the 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?

The input schema already describes both parameters (prompt and n) with 100% coverage. The description adds no additional explanation or examples beyond the schema, meeting the baseline for high schema 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 'AI图片生成（Qwen-Image）' clearly indicates the tool generates images using the Qwen-Image model, distinguishing it from image editing (baidu_image_edit) and video generation (baidu_video_gen) siblings. However, it could be more explicit about the text-to-image functionality.

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 like baidu_image_edit or baidu_vision_chat. There is no mention of use cases, prerequisites, or caveats.

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 full burden. It mentions cost and free quota but does not disclose other behaviors like error handling, supported image formats, rate limits, or response structure. This is minimal 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 a single concise phrase including cost info, which is front-loaded. It is not overly verbose, but could include more context without becoming too long.

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 one-parameter tool without output schema, the description is minimally complete. However, given many sibling tools with similar names, more context on what constitutes 'general objects' and response format would improve 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?

Schema coverage is 100% (one parameter with a description). The tool description adds no additional meaning beyond the schema. Baseline is 3; no extra value 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 does general object recognition (通用物体识别), using a specific verb and resource. It distinguishes from sibling tools like baidu_animal, baidu_car, etc., which focus on specific categories.

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 guidance on when to use this tool over siblings or alternatives. It only states the purpose and cost, leaving the agent to infer usage context without explicit when-to-use or when-not-to-use instructions.

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, and the description fails to disclose any behavioral traits such as whether the tool is read-only, destructive, or requires authentication. The only extra information is a cost and free quota, which does not illuminate 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 extremely concise (one line), but it lacks substance. Conciseness is achieved at the expense of clarity and completeness, making it insufficient for effective tool selection.

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 is simple with one parameter and no output schema, the description should provide at least a basic purpose. It fails to do so, leaving the tool's functionality unclear and incomplete.

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% coverage with one parameter described as '图片URL' (image URL). The tool description adds no additional meaning beyond the schema, merely echoing the parameter name in a different language.

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 is a mix of English and Chinese, stating '图片审核' which translates to 'image review'. However, it lacks a clear verb and resource specification, making it ambiguous among sibling tools. It does not distinctly define the tool's function.

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. There is no mention of use cases, prerequisites, or exclusions, leaving the agent without direction for selection.

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

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

With no annotations, the description carries the full burden. It discloses pricing ($0.02/call) and rate (5 free per day), which is a behavioral trait, but it fails to mention whether the tool is read-only, what it requires (e.g., image format constraints), or any side effects. The lack of behavioral detail limits 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 very concise: a single line conveying purpose and pricing. Every part is relevant and not wasteful. However, it lacks structure (e.g., separate sections) and includes non-functional info (pricing) that could be external, but the conciseness is effective.

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 simplicity (1 param, no output schema), the description is incomplete. It does not explain what the tool returns (e.g., a list of ingredient names, confidence scores), how to interpret results, or any limitations. For a vision recognition tool, the agent needs more context to handle the response 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% for the single parameter 'image' (described as '果蔬图片URL'). The description does not add meaning beyond the schema; it merely restates the tool's purpose. Baseline 3 is appropriate since the schema already sufficiently describes the parameter.

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 '果蔬识别' (fruit and vegetable recognition), indicating a specific verb (recognize) and resource (ingredients). This distinguishes it from sibling tools like baidu_plant (plants) and baidu_dish (dishes). However, it lacks an explicit verb in English and does not elaborate on the scope beyond fruits and vegetables.

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 baidu_dish or baidu_plant. The description does not mention any context, prerequisites, or exclusions, leaving the agent without decision support.

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 should disclose behavioral traits. It mentions pricing and free quota, which is useful, but lacks statement on non-destructiveness or idempotency.

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 short and front-loaded with category and pricing. It is efficient, though could be slightly expanded for completeness.

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

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

The tool has no output schema, so the description should explain what the tool returns. It does not, leaving the agent uncertain about the response format.

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%, and the schema already describes the single parameter as '待提取文本'. The description adds no additional parameter-level meaning.

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 name 'baidu_keyword_extraction' combined with '[NLP]' and '关键词提取' clearly indicates the tool extracts keywords from text. However, it does not explicitly distinguish from sibling NLP tools like sentiment or summary.

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 on when to use this tool vs alternatives. With many sibling NLP tools, explicit context for selection would help.

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 bears full responsibility. It only mentions pricing and a free tier, but omits behavioral traits such as accuracy, supported landmark categories, rate limits, or that it is a read-only operation.

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 (one line), but it is front-loaded with the category and purpose. However, it lacks structured information like output format or usage notes, making it minimally adequate.

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 tool with one parameter and no output schema, the description does not explain the return value or provide examples. The agent lacks context on what information the tool returns (e.g., landmark name, confidence score, location) and any image constraints.

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% (the single 'image' parameter has a description '地标图片URL'). The tool description adds no additional meaning beyond what the schema provides, so it meets the baseline for high 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 states '地标识别' (landmark recognition) under a Vision category, clearly indicating the tool identifies landmarks from images. The name 'baidu_landmark' and sibling tools (e.g., baidu_animal, baidu_plant) further differentiate its purpose.

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 alternative vision tools like baidu_object_detect or baidu_ocr. There is no description of prerequisites, preferred image types, 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 carries full burden. It only discloses pricing and quota, omitting behavioral traits like idempotency, side effects, auth needs, or whether it is read-only.

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 one line, starting with a clear tag '[LLM]'. It efficiently includes cost info but could be slightly more 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 the lack of output schema and many sibling tools, the description is incomplete. It does not explain return values, constraints (e.g., max tokens), or differentiate from other chat tools.

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 the baseline is 3. The description adds no additional meaning beyond what the schema provides, except for cost context which is not parameter-specific.

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 identifies it as an LLM dialogue tool for the ERNIE series, distinguishing it from other Baidu tools like baidu_deepthink or baidu_vision_chat. However, it lacks explicit mention of general conversational capabilities.

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 on when to use this tool versus similar siblings like baidu_deepthink or baidu_vision_chat. The description only provides cost and free quota info, not context for selection.

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

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

The description does not disclose any behavioral traits such as read-only hint, error behavior, or response structure. With no annotations present, the tool's behavioral attributes are entirely unspecified beyond the basic function, which is insufficient for an AI agent to understand side effects or limitations.

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 short, which is good for conciseness, but it mixes functional purpose with pricing information. The structure could be improved by separating pricing into annotations. Each sentence earns its place, but the inclusion of pricing in the description is somewhat misplaced.

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 and the simple nature of the tool, the description should inform about return values, confidence scores, or supported logo types. It provides only the basic function and pricing, leaving the agent underinformed about expected outputs.

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 only parameter 'image' is described in the schema as 'Logo图片URL', and the tool description adds no further meaning. Since schema description coverage is 100%, the baseline is 3. The description does not enhance understanding of the parameter beyond what the schema already provides.

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 'Logo识别' (Logo recognition), making the tool's purpose clear as recognizing logos from images. However, it does not differentiate from sibling vision tools like baidu_landmark or baidu_object_detect, so it lacks sibling differentiation. The inclusion of pricing is extraneous.

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. There are many sibling vision tools, but the description gives no context for selection, e.g., when to prefer logo recognition over object detection or landmark recognition.

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. The description does not disclose behavioral traits such as whether it is read-only, rate limits, authentication needs, or side effects. The only extra information is pricing ($0.01/call, free quota), which is transactional, not behavioral.

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?

Description is very concise (one sentence). It front-loads the purpose with '[NLP]' and includes pricing info which may be useful for cost-aware agents. However, the structure is minimal and could be improved with clearer separation of purpose and usage notes.

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 (one param, no output schema, no annotations), the description is minimal. It does not explain return values, typical use cases, or how it differs from similar NLP tools among siblings. The tool is simple, but more context would aid agent selection.

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 one parameter 'text' described as '待分析文本'. The description does not add meaning beyond the schema, but as per guidelines, baseline is 3 for high coverage. No further elaboration on format or constraints.

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 states '词法分析（分词+词性标注）' which clearly indicates lexical analysis (word segmentation and POS tagging). The '[NLP]' prefix groups it under NLP tasks. However, it does not explicitly distinguish from sibling tools like baidu_sentiment or baidu_keyword_extraction, though the specific task is clear.

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 on when to use this tool versus alternatives. The description only states what it does but does not mention prerequisites, context, or when not to use it. Sibling tools like baidu_keyword_extraction or baidu_sentiment perform different NLP tasks, but no comparison is provided.

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. The description only mentions cost and free quota, with no disclosure of behavioral traits like detected object categories, limitations, or expected output. This is insufficient for a tool with no annotation support.

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 short and front-loaded with cost info, but it sacrifices essential details. It is concise but incomplete, earning a middle score.

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 a single parameter, no output schema, and no annotations, the description should provide more context about what objects can be detected and how results are returned. The minimal entry is inadequate for complete understanding.

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% coverage for the single parameter 'image' with description '图片URL'. The description adds no additional meaning beyond the schema, such as image format or size requirements, and the Chinese schema may not be fully helpful for an English AI agent.

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 includes '通用目标检测' (general object detection) and the tool name suggests object detection, but it does not explicitly state the action in English. It vaguely indicates the purpose but does not distinguish from sibling tools like baidu_vehicle_detect or baidu_animal.

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 baidu_animal or baidu_vehicle_detect. The description lacks context for selection.

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

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

No annotations are provided, and the description fails to disclose any behavioral traits such as required authentication, input constraints, output format, or side effects. The description only states pricing.

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 brief but under-specified. While it is concise, it fails to provide necessary context, making it inadequate for the tool's complexity.

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 one parameter, no output schema, and many similar siblings, the description is severely incomplete. It lacks details on return values, image format requirements, and use cases.

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 one parameter 'image' with a description '图片URL', achieving 100% schema coverage. The tool description does not add any additional meaning beyond what the schema provides, so 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 is a label in Chinese ('通用文字识别（高精度版）') with pricing, but does not clearly state the tool's function in English. It vaguely implies general text recognition but does not distinguish it from the many other OCR sibling 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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of appropriate use cases, limitations, or exclusions.

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

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

No annotations provided. The description adds cost and free quota info but lacks details on input validation, error handling, performance, or supported languages. It partially covers behavioral aspects.

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, efficient line with key info front-loaded: [OCR] and version. No wasted words, but could be slightly more informative without losing conciseness.

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 1 param and no output schema, the description should hint at return values or capabilities. It only mentions cost and version, missing crucial context like output format or success/failure behavior.

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 the sole parameter 'image' having a description '图片URL'. The description adds no extra meaning beyond the schema, such as format or size limits. 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 it's for OCR text recognition with high accuracy, including cost and free quota. However, it does not differentiate from sibling OCR tools like baidu_ocr (standard) or baidu_ocr_handwriting.

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 on when to use this tool versus alternatives. The description mentions 'high precision' but does not explicitly state use cases, prerequisites, or exclusions.

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

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

No annotations exist, and the description only mentions cost and free quota, not behavioral traits like authentication, rate limits, or expected input/output 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 short and includes pricing info, but could be slightly more descriptive about the tool's 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?

For a simple tool with no output schema and no annotations, the description lacks details on expected image format, return values, or limitations, leaving the agent underinformed.

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 the single parameter (image URL) is fully described. The description adds no extra meaning beyond the schema, so 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 explicitly states it is for bank card recognition (OCR), but doesn't differentiate from other OCR tools among siblings like baidu_ocr_accurate or baidu_ocr_handwriting.

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 on when to use versus alternatives (e.g., baidu_ocr for general OCR), and no prerequisites or context provided.

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. Description only includes pricing and quota, but does not disclose behavioral traits like read-only nature, error behaviors, or required permissions. The agent lacks insight into side effects or limitations.

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 short (one sentence), which is efficient, but it omits valuable information. It is not overly verbose, but the brevity comes at the cost of clarity in usage and 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 the tool has no output schema and only one parameter, the description should at least indicate the expected output format. It does not. The pricing info is helpful but insufficient for complete understanding.

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 a single parameter 'image' described as '图片URL'. The description adds no extra meaning beyond what the schema provides, so 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 '营业执照识别' (business license recognition), a specific OCR task. It distinguishes itself from sibling OCR tools like baidu_ocr, baidu_ocr_bankcard, etc., by specifying the document type.

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 on when to use this tool versus alternatives like baidu_ocr_accurate or baidu_qianfan_ocr. No context on prerequisites or expected image quality.

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 but only mentions cost and free calls. It does not disclose behavioral traits such as read-only status, authentication needs, rate limits, or output format.

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 at one line, front-loading the purpose. While it lacks structure, it has 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 the simplicity of the tool (1 param, no output schema), the description fails to explain what the tool does in sufficient detail or how to use it, especially in context of many similar sibling tools.

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 sole parameter 'image' is fully described in the schema as '图片URL'. The description adds no additional meaning, so it meets the baseline for 100% schema 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 is an OCR tool for office documents, but does not differentiate it from the many sibling OCR tools (e.g., baidu_ocr, baidu_ocr_accurate). The purpose is clear but lacks distinguishing details.

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 the numerous alternative OCR tools. The description lacks any context for appropriate usage scenarios.

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 includes pricing ($0.02/call) and free quota (5/5 today), which are behavioral traits beyond what annotations would provide (none exist). However, it omits other behavioral details like supported languages, image requirements, or rate limits, so it is only partially 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 extremely concise, using a single line to convey purpose, pricing, and quota. No redundant information is present, and the bracket prefix '[OCR]' adds quick categorization. However, it could be slightly more structured with separate sentences.

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 should explain return values but does not. It also lacks information on image format constraints, size limits, or language support. For a simple tool with one parameter, the description is incomplete, leaving the agent without critical usage 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?

The input schema has 100% coverage for its single parameter 'image', which the description does not elaborate on further. With full schema coverage, the baseline is 3, and the description adds no additional meaning beyond the schema's '图片URL'.

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 as handwriting OCR via the label '[OCR] 手写文字识别', indicating the specific resource and action. However, it does not explicitly differentiate from many sibling OCR tools like baidu_ocr or baidu_ocr_accurate, relying on the name 'handwriting' to distinguish.

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 vs alternatives such as baidu_ocr (general) or baidu_ocr_numbers. The description lacks context for ideal use cases or exclusions, leaving the agent to infer from the name alone.

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. The description includes pricing and free quota, which is helpful, but it does not disclose whether the tool is read-only, what limitations exist (e.g., only digits), or expected output format. This is insufficient behavioral 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 extremely concise, consisting of a single line with a tag, purpose, and pricing. It is front-loaded and contains no superfluous text. However, it is in Chinese, which may be a minor accessibility issue.

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

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

The tool has no output schema, so the description should explain what the tool returns. It does not. Given the complexity of multiple sibling OCR tools, the description lacks details on expected input format and return value structure, making it incomplete.

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 only parameter 'image' is described in the schema as '图片URL' (image URL). With 100% schema description coverage, the baseline is 3. The description adds no additional semantic meaning beyond the schema, such as image format requirements or expected content.

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 '[OCR] Digit recognition' clearly indicates the tool's purpose of recognizing numbers from images via OCR, distinguishing it from sibling tools like general OCR or handwriting OCR. However, it lacks an explicit verb like 'recognizes' or 'extracts', making it slightly less 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?

No guidance is provided on when to use this tool versus alternative OCR tools. Given the large number of sibling OCR tools (e.g., baidu_ocr, baidu_ocr_handwriting), the lack of usage instructions makes it difficult for an agent to select the correct 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?

With no annotations, the description is responsible for disclosing behavior. It only mentions cost and free calls, but omits critical details like whether the tool is read-only, what it returns, error handling, or any side effects.

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, using a single line for purpose and pricing. It is front-loaded with the tool type. However, it lacks a clear structure and could include more essential details without losing conciseness.

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 only one parameter and no output schema, the description should at least mention the output (e.g., decoded QR content) or how results are returned. It also fails to explain how this tool differs from other OCR tools for QR codes. The pricing info is helpful but insufficient.

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 parameter 'image' is fully described in the schema as '图片URL' (image URL). The tool description adds no further semantic information, but since schema coverage is 100%, the 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 explicitly states 'QR code recognition' and includes the category '[OCR]', making it clear that this tool decodes QR codes from images. It distinguishes from general OCR tools like baidu_ocr.

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 baidu_ocr or baidu_ocr_accurate. The description only includes pricing and free quota, which does not help with tool selection.

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

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

No annotations are provided, and the description only states the tool's function and cost. It does not disclose behavioral traits such as input requirements, output format, or any side effects. The description carries the full burden for behavioral transparency but fails to add meaningful context beyond the obvious.

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, fitting in a single line. It includes useful pricing and quota info without extra fluff. However, it could be better structured, e.g., separating pricing from 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 lack of annotations and output schema, the description is insufficient. It does not explain return values, image format requirements, or any limitations, leaving significant gaps for the agent.

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% coverage with a single parameter 'image' described as '图片URL'. The description adds no additional meaning beyond the schema, so 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 it's for seal/stamp recognition, using the Chinese term '印章识别', which is specific and distinguishes it from general OCR tools. The purpose is immediately understandable.

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 pricing and free quota info, which helps in cost-conscious decisions, but lacks explicit guidance on when to use this tool versus other OCR siblings (e.g., baidu_ocr, baidu_ocr_handwriting). No alternative names are mentioned.

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 full burden but only mentions cost and free quota. It does not disclose behavioral traits such as input format expectations, output structure, or potential limitations (e.g., only works with certain table types).

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 short and front-loaded with type and cost. While it could include more useful detail, it wastes no words and is efficient.

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 many sibling OCR tools and no output schema, the description is incomplete. It fails to explain what differentiates table OCR or what the agent should expect as output, limiting usability.

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% (one parameter 'image' with description '图片URL'). The description adds no extra meaning beyond the schema, so a baseline 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 states '表格文字识别' (table text recognition) with an '[OCR]' prefix, clearly indicating the tool's function of recognizing text in table images. It distinguishes itself from general OCR siblings like baidu_ocr, but could be more explicit in English.

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 on when to use this tool versus other OCR tools for tables, like baidu_ocr or baidu_ocr_accurate. The lack of context for selection among many siblings makes it difficult for an agent to choose correctly.

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 must fully disclose behavioral traits. It reveals the cost per call and that it handles web images (URL input), but fails to mention output format (e.g., text, confidence scores), error conditions, or whether it supports concurrent calls. The behavioral disclosure is inadequate.

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 (one line), but it omits essential details like what the tool returns. While it includes cost info efficiently, the brevity compromises completeness. A balanced description would be slightly longer to cover 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?

Given the tool's simplicity (1 parameter, no output schema) and many similar siblings, the description should clearly explain the tool's unique purpose and behavior. It partially covers purpose (web images) but lacks details on output, usage scenarios, and limitations, making it incomplete for effective agent 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?

The input schema fully describes the single 'image' parameter as a URL (图片URL) with 100% coverage. The description adds no additional semantic value beyond restating it handles web images. Baseline score of 3 applies since schema already covers the parameter meaning adequately.

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's for OCR on web images (网络图片文字识别), providing a specific verb (recognize) and resource type (web images). However, it does not explicitly differentiate from the many sibling OCR tools (e.g., baidu_ocr_accurate, baidu_ocr_handwriting), relying on the 'webimage' part of the name to imply distinction.

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 includes cost information ($0.02/call) and a free quota (5/5 today), which hints at usage conditions but does not provide guidance on when to use this tool over alternatives, such as when to choose webimage versus other OCR tools for different image types or accuracy needs.

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 must convey behavioral traits. It only mentions pricing and free calls, omitting details like whether the tool mutates state, required permissions, or supported languages. The agent cannot infer the system's behavior from this.

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 short, which is efficient, but it only provides a label and cost info; more substance is needed for a full understanding. It is front-loaded with the OCR tag.

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

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

The tool has no output schema and no annotations; the description fails to explain what the tool returns (e.g., text, coordinates). For a document parsing tool, this is a critical omission.

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% and the description adds no additional meaning beyond the parameter names and descriptions already in 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 labels this as '[OCR] PaddleOCR-VL 文档解析' which indicates document parsing OCR, but does not specify what kind of documents or output content. It fails to distinguish from sibling OCR tools like baidu_ocr_table or baidu_ocr_handwriting.

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?

There is no guidance on when to use this tool vs. the many sibling OCR tools. No when-to-use or when-not-to-use information is provided.

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 cost ($0.02/call) and free call limit (5/5 today), which are useful behavioral traits. However, it does not describe what the tool does beyond recognition (e.g., returns species list, confidence scores), and no annotations are provided to fill gaps.

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 no unnecessary words. Information is front-loaded with the [Vision] tag and pricing. However, the brevity omits important details, so it's not optimal.

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 one parameter and no output schema, the description is too minimal. It does not explain the response format, accepted image types, or potential errors. The pricing info is helpful but insufficient for an agent to understand what the tool returns.

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% for the single parameter 'image', with a clear description specifying it expects a plant image URL. The tool description adds no additional meaning beyond the schema.

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

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

The description clearly states it performs plant recognition (植物识别), distinguishing it from sibling tools like baidu_animal and baidu_car. However, it does not specify what information is returned (e.g., species name, confidence), which slightly reduces clarity.

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 explicit guidance on when to use this tool versus alternatives. The name and [Vision] tag imply usage for plant images, but there is no mention of image requirements (e.g., format, size) or when not to use.

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 mentions 'free: 5/5 today' indicating a daily usage limit, but does not disclose any other behavioral traits such as whether it modifies data, authentication needs, or rate limits beyond the free quota. No annotations exist to supplement.

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 short (one line), which is concise but lacks structure. It packs the tool name, context size, and pricing into a single sentence, but misses the opportunity to organize information for quick scanning.

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

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

Given the absence of an output schema and many sibling OCR tools, the description is incomplete. It does not explain the return format, supported image types, or how this OCR differs from others (e.g., baidu_ocr_handwriting, baidu_ocr_table).

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 descriptions for both parameters are provided ('图片URL' and '识别指令(可选)'), so baseline is 3. The tool description adds no additional semantics to the parameters, such as format constraints or examples.

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 identifies the tool as an OCR tool with 'Qianfan-OCR 32k上下文通用OCR', clearly stating it performs optical character recognition. However, among many sibling OCR tools, it does not specify what makes it distinct (e.g., 32k context vs others).

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 guidance on when to use this tool versus alternative OCR tools like baidu_ocr, baidu_ocr_accurate, baidu_vision_chat, etc. There is no mention of scenarios, prerequisites, or when to avoid.

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, and the description only includes pricing information. It does not disclose behavioral traits such as read-only nature, rate limits, or authorization requirements. The agent gets no behavioral insight beyond the bare name.

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 short but at the expense of useful information. It is under-specified rather than concise. A better description would provide purpose and usage in a few sentences.

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 two required parameters and no output schema, the description is incomplete. It does not explain what reranking does, how the output is formatted, or in what scenarios it should be used. The agent lacks essential context to use 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 100%, with clear Chinese descriptions for both parameters ('query term' and 'document list separated by ||'). The description adds no additional meaning beyond what the schema already provides, so it meets the baseline of 3.

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

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

The description labels the tool as '重排序（BCE-Reranker）' which indicates reranking, but does not explain what it does clearly in English or NLP terms. It is vague and does not distinguish it from sibling tools like baidu_nlp.

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 usage guidelines are provided. The description does not specify when to use this tool versus alternatives, nor does it give any context on prerequisites or exclusions.

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

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

No annotations provided, so description carries full burden. It only states the basic function without disclosing behavioral traits like rate limits, request limits, or output specifics. The pricing info is included but not behavioral.

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?

Very short and to the point, but includes pricing info which is somewhat extraneous. However, it does not waste words and is easily scannable.

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?

Tool has one parameter and no output schema, yet description does not explain return values or behavior. For an NLP tool, more context on output format would be helpful. Incomplete for an agent to fully understand usage.

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 a single parameter described in the schema (待分析文本). The description adds no additional meaning beyond the schema's description, so 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 it's for sentiment analysis (positive/negative judgment), using specific verb and resource. It distinguishes from sibling tools like baidu_nlp and baidu_keyword_extraction by focusing on sentiment polarity.

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 usage via the NLP tag and sentiment focus, but no explicit when-to-use or when-not-to-use. No alternatives or exclusions mentioned, though context suggests it for sentiment tasks.

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. The description only mentions pricing, but no behavioral traits like input constraints, output format, response time, or error conditions. The agent has no insight into side effects or limitations beyond the basic function.

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 short and front-loaded with '[NLP]' category. It efficiently conveys the core function, though it could benefit from slightly more structure, such as bullet points for key attributes.

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 single parameter and no output schema or annotations, the description is minimal. It lacks details on input length limits, supported languages, return format, or any caveats, leaving the agent underinformed.

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 one parameter 'text' described as '待摘要文本' (text to summarize). The description adds no additional meaning beyond the schema, so 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 it is an NLP tool for text summarization ('文本摘要（自动生成摘要）'). The name and description together indicate its function, but it does not explicitly differentiate from siblings like baidu_nlp or baidu_sentiment, though the summarization task is 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?

No guidance on when to use this tool versus alternatives, such as baidu_nlp or baidu_keyword_extraction. No mention of prerequisites, context, or when not to use it.

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 must disclose behavioral traits. It only mentions cost and a daily free limit, but does not clarify whether it modifies input, returns corrections, or any side effects. The correctness behavior 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 very short and front-loaded with a tag. It efficiently conveys the core purpose and pricing, though it sacrifices some clarity. It could be slightly more informative without adding length.

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 simple input schema and no output schema or annotations, the description should provide more context about the output format or usage. It lacks completeness, leaving the agent uncertain about what the tool returns.

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% for the single parameter 'text', which already has a description ('待纠错文本'). The tool description adds no additional meaning, such as constraints on text length or encoding, so it meets the baseline 3.

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

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

The description states the tool does text correction ('文本纠错'), which provides a verb and resource. However, it lacks specifics such as language support or scope, and does not differentiate it from siblings like baidu_nlp. The pricing info is ancillary.

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 given on when to use this tool versus alternatives such as baidu_nlp or baidu_sentiment. There is no mention of prerequisites, context, or when not to use it.

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 fails to disclose behavioral traits such as whether the tool is destructive, required authorization, rate limits, or return format. The minimal description adds no 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 very short and efficient, with no wasted words. It includes useful pricing and free quota info, though it could be slightly more structured (e.g., separating core function from pricing). Still, it earns its place.

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

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

Despite low complexity (single param, no nested objects), the description lacks critical context. No output schema is provided, so the description should explain what the tool returns (e.g., pass/fail, categories). Without this, the agent cannot fully understand the tool's usage.

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 one parameter ('text') having a description. The tool description adds no additional meaning beyond what the schema provides, so 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 explicitly states '文本审核' (text review) with categories in parentheses (pornography/violence/politics), making the purpose clear. The [NLP] tag and pricing info provide additional context. It distinguishes from sibling tools like baidu_image_review by focusing on text.

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

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

The description implies usage for text content moderation but provides no explicit guidance on when to use this tool versus alternatives (e.g., image review or other NLP tools). No exclusions or scenarios are mentioned.

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?

Description includes pricing info and free usage limit, which are behavioral traits. However, it doesn't disclose supported languages, language code format, or error behaviors. With no annotations, the description partially covers behavioral disclosure.

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, with purpose front-loaded in brackets. However, it could include more context without being lengthy.

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?

Missing crucial details like supported language codes, how to specify languages, and response format. As a translation tool with 3 parameters and no output schema, more context is needed 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 100%; the description adds no extra meaning beyond the parameter names and brief schema descriptions. Baseline 3 is appropriate since the schema does the heavy lifting.

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

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

Clearly states it's a translation tool (多语种翻译) and includes pricing. The title and description distinguish it from sibling Baidu tools which are other services like OCR, image analysis, etc.

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 usage: use for translation. No explicit guidance on when to use vs alternatives (e.g., other translation tools), nor when not to use.

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 full burden but discloses almost no behavioral traits. It does not mention whether the operation is read-only or destructive, nor does it describe any side effects, output format, or rate limits beyond cost.

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 with one sentence including a cost note. No wasted words, but the brevity sacrifices clarity in other dimensions.

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 tool with one parameter and no output schema, the description lacks important details such as supported text length, audio format returned, and whether the operation is synchronous. While complexity is low, the description is insufficient for an agent to reliably understand the tool's complete behavior.

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 single parameter 'text' has a schema description ('要转语音的文字'), and the tool description adds no further semantic value. Since schema coverage is 100%, the 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 indicates this is a text-to-speech tool via the Chinese label '文字转语音（TTS）'. It is distinct from siblings as the only TTS tool among them. However, it does not explicitly state the action in English.

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 on when to use this tool versus alternatives. Only cost information is provided, which is not usage guidance. No mention of prerequisites, text length limits, or language constraints.

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. The description only includes pricing and free tier info, lacking any disclosure about side effects, response behavior, or error handling.

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 short, but includes pricing info which may be considered peripheral. Still, it is concise and front-loads 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?

For a simple tool with one parameter and no output schema, the description is incomplete. It lacks any detail about the output format, behavior, or 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?

The only parameter 'image' has a brief description in the schema, and schema coverage is 100%. The description adds no extra meaning beyond the schema, so 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 it detects vehicles and returns location and type, which matches the tool name. However, it does not distinguish from sibling tools like 'baidu_object_detect' or 'baidu_car'.

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 on when to use this tool versus alternatives. No prerequisites, constraints, or conditional logic mentioned.

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 but fails to disclose any behavioral traits. It does not mention if the operation is read-only or destructive, rate limits, or what happens to inputs. The pricing note is not behavioral. Transparency is low.

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 (one line), but it lacks structure and essential information. It is not front-loaded with key details; it merely states a category and pricing. While brief, it sacrifices completeness for brevity.

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 two required parameters and no output schema, the description should explain the expected output or behavior. It does not mention return format, any limitations, or required setup. Completeness is insufficient for a video generation 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% with both parameters having Chinese descriptions ('参考图片URL' and '视频描述'). The tool description adds no additional meaning beyond what the schema provides, so baseline 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 indicates video generation (视频生成) and names the model (MuseSteamer), which provides a basic purpose. However, it does not explain what the tool does beyond the name, such as generating a video from a reference image and prompt. It distinguishes from siblings like baidu_video_query and baidu_image_gen, but the clarity is minimal.

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. There is no mention of context, prerequisites, or when not to use it. The description only includes pricing and free call info, which does not help in tool selection.

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

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

No annotations are provided, and the description only states the tool's purpose without disclosing any behavioral traits such as side effects, authorization needs, or rate limits. For a query tool, it is likely safe, but the description does not confirm this.

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 short and front-loaded with the purpose. It includes pricing info which may be useful but not essential. No unnecessary text, though the structure is minimal.

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 simplicity (one required parameter, no output schema), the description should at least indicate what the tool returns, such as status or result of a video generation task. It lacks this information, making it incomplete.

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?

There is only one parameter, task_id, with a Chinese description '任务ID' in the schema. Schema coverage is 100%, so the description adds no additional meaning. The baseline 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 it is a query for video generation tasks. The [Video] prefix and text '视频生成任务查询' make the purpose clear, distinguishing it from sibling tools like baidu_video_gen which likely handles creation. However, it could be more specific about what the query returns (e.g., status, result).

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 explicit guidance on when to use this tool versus alternatives. The sibling list includes baidu_video_gen for generation and baidu_video_query for querying, but the description does not provide context or exclusions, leaving the agent to infer usage from the name alone.

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 full burden but only discloses cost and free quota. It does not state whether the tool mutates data, requires authentication, or has side effects. Behavioral traits like response format or data handling are absent.

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 line that conveys essential information: tool function, model name, and pricing. It is concise and avoids redundancy, though it could be more 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 no output schema, the description should hint at return values but does not. It lacks information on what the agent can expect as output, such as answer text or confidence scores. For a multimodal chat tool, this is a notable gap.

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 the schema already documents the two parameters. The description adds minimal meaning beyond '图片URL' and '提问内容' by hinting at a chat interaction. It does not clarify expected input formats or constraints.

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 indicates this is a visual understanding dialogue tool using ERNIE-VL multimodal model, which distinguishes it from siblings like baidu_llm_chat (text-only) and baidu_image_recognition (classification). However, it lacks an explicit verb like 'answer' or 'process' and does not state the action clearly.

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 on when to use this tool versus alternatives such as baidu_object_detect or baidu_deepseek_ocr. The description only provides pricing and does not mention context 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?

With no annotations, the description carries the full burden of disclosing behavioral traits. It only mentions pricing and free quota, but does not describe what the tool returns, any input constraints, error behavior, or other relevant details. The agent lacks essential information about the tool's 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 brief and front-loaded with the NLP tag and purpose. It contains no superfluous information, making it efficient. However, it could be slightly restructured to include more useful information without increasing length excessively.

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 low complexity (one parameter, no output schema), the description should at least explain the return value format to help the agent use the embedding correctly. It fails to do so, leaving the agent uncertain about the output, which is critical for a word embedding 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 has 100% coverage with a single parameter 'text' described as '词语' (word). The description adds context that it is an NLP word embedding tool, but does not significantly expand on the schema's meaning. The baseline score of 3 is appropriate as the schema is already sufficient.

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 states the tool does '词向量表示' (word embedding representation), clearly indicating its purpose as an NLP tool for generating word vectors. However, it does not differentiate from sibling tools like 'baidu_embedding' or 'baidu_nlp', which may have overlapping functionality.

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. The description only includes a tag '[NLP]' and pricing, but does not explain the specific use case for word embeddings compared to other NLP tasks (e.g., sentiment analysis, summary).

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 provides the daily call limit and free status. This is helpful but does not disclose the return format or any side effects. For a simple price query, this is minimally adequate.

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 short, which is concise, but the inclusion of 'Free/call (free: 5/5 today)' is somewhat cryptic and could be clearer. It front-loads the essential info but the parentheses could be confusing.

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 simplicity and lack of parameters, the description covers the main purpose and usage limit. However, without an output schema, the agent does not know the format of the returned data, which could be improved.

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 the input schema is empty. Per the guidelines, 0 parameters gets a baseline of 4. The description adds the free pricing info, which is relevant.

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 'BTC real-time price' which directly indicates the tool's function. However, it does not explicitly distinguish it from sibling tools, but given that no other sibling is related to Bitcoin price, the purpose is fairly clear.

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 mentions it is free and provides the daily call limit, which gives some usage context. However, it does not specify when to use this tool versus alternatives, nor does it mention any prerequisites or situations to avoid its use.

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 behavior. It discloses that the call is free with a limit ('free: 5/5 today'), which is useful. However, it does not mention other traits like response format, latency, or error handling. For a parameterless tool, 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 very concise at 13 words, front-loading the free nature and the resource. Every phrase adds value: it specifies the tool's purpose, free status, and usage limit. It could be slightly more structured but is efficient.

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 parameters, no output schema, and simple functionality, the description is reasonably complete. It explains the tool's purpose and key constraint (free limit). However, it omits details about output structure or how to interpret gas fees, which might be inferred but not explicitly stated.

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 parameters, so the description does not need to add parameter details. With 100% schema coverage (by default), the baseline is 4. The description adds no further parameter information, which 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 it is for querying Ethereum gas fees, using the verb '查询' (query) and specifying the resource '以太坊Gas费'. This distinguishes it from sibling tools like btc_price or weather, which are different domains.

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 explicitly state when to use this tool versus alternatives. It mentions it is free with a daily limit, but no guidance on when to prefer gas_price over other price-related tools. Usage is implied by the resource name, but not elaborated.

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 indicates a read operation but does not explicitly state it is read-only, nor does it disclose any behavioral traits such as authentication requirements or rate limits. Given the lack of annotations, the description carries the full burden and provides minimal 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 a single concise sentence that is front-loaded with the essential action and resource. Every word is purposeful, with no unnecessary 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 has no parameters and no output schema, the description adequately covers the purpose and output content. It could be more detailed about the return format, but it is complete enough for a simple status check 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?

There are no parameters, and the schema coverage is 100%. The description adds value by specifying the output content (free calls, pricing, categories), which goes beyond the empty schema. Baseline for zero parameters is 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 the verb 'View' and the resource 'GoldBean MCP status', and lists the specific information shown (free calls remaining, pricing, categories). It distinguishes itself from sibling tools, which are about AI, price, weather, etc.

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

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

The description implies usage for checking status, but does not provide any guidance on when to use versus alternatives or when not to use. No explicit context or exclusions are given.

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

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

No annotations provided; the description only mentions free call limit and the basic function, without detailing behavior such as data sources, update frequency, or any constraints beyond the call limit.

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 short and front-loaded with the essential info (weather query and free limit). However, the inclusion of free call limit interrupts the main purpose, though it is still concise.

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 simplicity (1 param, no output schema), the description still fails to explain what the output looks like or any return format. Missing details reduce completeness for an agent.

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%, and the single parameter 'city' is described as '城市名' (city name). The description adds no extra semantic meaning beyond what the schema provides, so baseline score 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 states '实时天气查询' which clearly indicates a real-time weather query tool. However, it does not differentiate from sibling tools like btc_price or gas_price, which are also query tools for specific data.

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 on when to use this tool versus alternatives. The description only mentions a free call limit, not the appropriate context for weather queries.

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