AdsTurbo

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

With annotations provided, the bar for adding context is lower, but the description adds almost nothing beyond what annotations already cover. It does not explain what 'analysis' entails, what the output is, or any side effects. Annotations indicate a non-read-only, open-world operation, but the description does not elaborate.

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, consisting of only a title-like phrase. While concise, it lacks front-loaded useful information and does not earn its place by adding value beyond the tool name.

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 that performs analysis and generates a prompt, the description is severely lacking. It does not explain what the analysis produces, how the prompt is used, or any dependencies. Given the absence of an output schema, the description should compensate, but it does not.

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 fully documents the three parameters (video_url, clip_start, clip_end) including constraints. The description provides no additional parameter information, which is acceptable given the 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 name and description indicate a video cloning analysis capability (视频复刻 — 分析). However, the description is extremely short and lacks a clear verb+resource structure that distinguishes it from sibling tools like ad_clone_generate or video_analyze. The purpose is implied but not explicitly stated.

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 ad_clone_generate or video_analyze. The description offers no context, 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?

Annotations already declare this is a non-read-only, non-idempotent, open-world operation, and the description adds nothing beyond that. It does not mention the asynchronous task model or that the response returns a task ID (that context lives only in the schema description, not the tool description), and it does not contradict the annotations.

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

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

It is a single, front-loaded label with no waste, but for a five-parameter asynchronous generation tool it is under-sized rather than appropriately concise, conveying almost no operational content.

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

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

Given a 5-parameter async generation tool with no output schema, the description should explain the submission/polling model and the Analyze prerequisite. It omits both, leaving the workflow context to the schema description and the sibling list.

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 every parameter (ratio, prompt, duration, video_url, callback_id) is already documented inline with defaults and the Analyze linkage. The tool description adds no parameter meaning, so 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?

"视频复刻 — 生成" names a resource (video clone) and an operation (generate), so the agent can infer this creates a cloned video. But it is essentially a restatement of the name ad_clone_generate in another language, with no scope detail and only implicit differentiation from ad_clone_analyze.

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

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

The description gives no indication of when to use this tool versus siblings, nor does it state the prerequisite workflow. The dependency on ad_clone_analyze (whose returned video_segment_url feeds video_url) is only hinted at inside the schema, not in the tool 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds nothing further — no mention of pagination behavior, result volume, or how the enum filters combine — so it contributes no behavioral context of its own.

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?

Seven characters is not concise, it is under-specified. There is no wasted language, but the single noun phrase carries too little content to be considered appropriately sized for a 10-parameter filtering 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?

For a tool with 10 filter parameters, no required params, no output schema, and no annotations describing return behavior, the description supplies none of the missing context: not the meaning of the enum dimensions, not pagination defaults, not the shape of the returned list.

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 10% across 10 parameters; only industry (and the root schema note about lowercase/hyphenated values) is documented. The description says nothing about any parameter — no explanation of array-vs-scalar semantics, sort_by values, enum meanings, or how filters are AND/OR-combined — so it fails to compensate for the large coverage gap.

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

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

"系统演员列表" is essentially a Chinese restatement of the tool name ai_actor_list — a noun phrase with no verb and no scope detail. It does not distinguish itself from siblings like ai_actor_perform or ai_actor_say beyond the trivially obvious "list" semantics already in the name.

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 call this tool, when not to, or which sibling to prefer for related tasks (e.g. ai_actor_perform for generating an actor action). The agent must infer usage entirely from the name and sibling list.

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

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful trait beyond the annotations: the invocation returns an asynchronous task response ('异步任务响应'), telling the agent not to expect an inline result. It does not, however, explain how to poll for completion (get_work_status/get_persona_status) or how the callback_id webhook fits in.

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

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

Two short sentences, purpose front-loaded and the actor_id clarification second; nothing in the text is redundant padding. It is tight, though arguably tighter than a 9-parameter async tool warrants.

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, zero-required-parameter mutation with no output schema and 78% of parameters undescribed, the description is far too thin. It signals async behavior but omits the polling/webhook follow-up and leaves most inputs unexplained, so an agent cannot call it confidently.

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 only 22% — just actor_id and callback_id are documented. The description adds meaning for actor_id (system actor ID vs Persona actor_id sharing one parameter set), but the remaining seven parameters (speed, style, script, stability, similarity, auto_emotion, speaker_boost) are undocumented in both schema and description, and 'shared performance parameters' is too vague to fill that gap.

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

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

The opening '演员演出（系统演员或 Persona）' largely restates the tool name and adds only the scope qualifier that the actor may be a system actor or a custom Persona. It never says what a 'performance' actually produces (audio, video, animation) and does not distinguish this from the sibling ai_actor_say or ai_actor_list. Purpose is inferable but thin.

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 when-to-use or when-not-to-use guidance and no mention of alternates such as ai_actor_say (which sounds like the synchronous counterpart) or ai_actor_list. The only usage hint is that actor_id accepts either a system actor or a Persona, which is a compatibility note rather than routing guidance.

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

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=false, and destructiveHint=false, which tells the agent this is a non-idempotent local write-ish operation. The description adds nothing beyond restating the tool name — no mention of cost, actor availability requirements, persistence of generated audio, or how repeated calls differ.

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, but this is under-specification rather than conciseness — a single six-character noun phrase that omits all operational detail the agent needs.

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

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

With no output schema, no sibling differentiation, six undocumented parameters, and a one-line description, the definition is far too thin for a 6-parameter synthesis tool. Nothing tells the agent how to form a valid call or what comes back.

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?

Six parameters exist (script, actor_id, speed, stability, similarity, auto_emotion) with 0% schema description coverage, so the description carries the full burden. It documents none of them, leaving the agent to guess at value ranges, units, or which are required.

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 phrase "系统演员语音生成" identifies the resource (system actor voice) and an implied action (generate), so an agent can roughly infer text-to-speech for a virtual actor. However, it is a terse noun phrase with no verb framing and gives no basis for distinguishing it from siblings like ai_actor_perform, ai_actor_list, or video_lip_sync.

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 versus alternatives such as ai_actor_perform or the video generation tools. No prerequisites, no exclusions, no context about actor selection is offered.

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?

注解已提供 readOnlyHint=true、idempotentHint=true、destructiveHint=false，因此安全配置已明确。描述没有添加任何信息，例如空 workspace_ids 的行为、缺失 ID 是否会被静默跳过，或返回的负载形态。

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?

一个简洁的短语，没有赘述，但过短接近于信息不足，而非高效表达。

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?

对于一个单参数只读工具，其基本信息足以调用，且没有输出 schema 需要解释。但它缺少与同类工具 get_work_status 以及可能的 get_persona_status 进行比较时所需的指导。

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 描述覆盖率为 0%，只有一个未记录的数组参数，因此描述必须承担解释 workspace_ids 的责任。它仅通过 "批量" 暗示了多重性，对格式、上限或无效值处理未作任何说明。

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?

明确动词+资源：批次查询异步任务状态。"批量" 表明它与单目标 get_work_status 同级的区别，无需查看其他 schema。

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?

未说明何时使用此工具而非 get_work_status、是否允许空列表，或应当优先使用批量还是单个。其使用方式仅能从 "批量" 这个词推断。

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered externally. The description adds nothing beyond that – it does not say what 'status' values exist, what an unknown/missing actor returns, or whether the persona must already exist.

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 single sentence is front-loaded and free of filler, but at this length it is under-specified rather than truly concise; there is no structural content to speak of.

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 one-parameter lookup tool with no output schema, annotations, or sibling routing, the description is too thin: it never defines the returned status concept or distinguishes itself from persona_list or the work-status 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 single actor_id parameter has no property-level description (0% schema coverage), and the description does not explain what actor_id is, whether it is optional, or what happens if it is omitted. The description fails to compensate for the schema gap.

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

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

The description names a verb (查询) and a resource (Persona 状态), so the basic action is identifiable. However it gives no differentiation from siblings like persona_list, get_work_status, or batch_get_work_status, leaving the agent to guess which status-retrieval tool applies.

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 indication of when to call this versus persona_list or the other status/query tools, and no prerequisites or exclusions are stated. Usage must be inferred entirely from the name.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds nothing beyond that: no polling/async semantics, no explanation of what the status response contains or whether the workspace must exist. It fails to earn value beyond the structured fields.

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?

It is a single short sentence, front-loaded with the core action, so nothing is wasted. But the extreme brevity functions as under-specification rather than efficient conciseness for a tool with an undocumented parameter and a near-identical sibling.

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

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

With no output schema to explain return values and no parameter documentation, the description should carry more of the load. It omits what 'status' means, what the returned states are, how it relates to batch_get_work_status, and the role of workspace_id, leaving real gaps 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 0% and the single workspace_id parameter has no format, required-ness, or example detail. The description's single short clause mirrors the schema-level note and adds no syntax or constraint information to compensate for the coverage gap.

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

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

The description states a clear verb+resource combination ('查询异步任务状态' / query async task status), so an agent knows the tool reads task status. However, it does not differentiate from the extremely close sibling batch_get_work_status, nor clarify that the query is scoped by workspace rather than a single task, so it falls short of a 5.

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 when-to-use guidance, no mention of when to prefer this over batch_get_work_status or get_persona_status, and no stated prerequisites. The agent must infer usage purely from the name.

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

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds nothing beyond that — it does not explain the async/callback workflow implied by callback_id and workspace_id, nor what the tool produces.

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?

A four-character phrase is not conciseness but under-specification: there is no structure, no front-loaded scope, and no information an agent can act on beyond the noun. Every possible sentence that would earn its place is absent.

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 7 parameters, zero required fields, async-task fields (callback_id, workspace_id) and no output schema, the description should carry significant explanatory weight. Instead it offers a single phrase, leaving the async submission model, method options and output behavior entirely unexplained.

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 every one of the 7 parameters (method, image_url, resolution, callback_id, workspace_id, output_format, idempotency_key) is documented in the schema itself. Per the baseline rule for high coverage, a 3 is appropriate since the description adds no parameter detail.

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

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

"图片抠图" names a specific verb+resource (image cutout/background removal), which is more than a tautology of the tool name. However, it offers nothing to distinguish it from sibling tools like image_magic_eraser or image_enhance, which operate on similar image-editing ground.

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 when-to-use guidance, no prerequisites, and no mention of alternatives among the 29 sibling tools. The agent must infer from the name alone that this is for background removal rather than erasing objects or enhancing 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?

Annotations already declare this is a non-read-only (readOnlyHint=false), open-world (openWorldHint=true), non-idempotent write operation, so the safety profile is partly covered. However, the description adds nothing at all – no mention of long-running generation, callback/idempotency semantics, or cost – despite the tool clearly performing a generative write.

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?

Four characters is not conciseness but under-specification; there is no front-loaded purpose statement and no structure to speak of. Nothing here earns its place because nothing meaningful is said.

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 10-parameter generative write tool with no output schema and an open-world, non-idempotent profile, the description is completely inadequate. An agent has no idea what the tool returns, how long it takes, or how to choose it over sibling image 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 description coverage is 100% across all 10 parameters, so the baseline is 3 even though the description contributes no parameter meaning. The schema labels themselves are terse (e.g. "语言", "输出分辨率") but they are at least present.

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?

"电商产品图" (e-commerce product image) is a noun phrase that essentially restates the tool name image_ecommerce; it never states a verb or whether the tool generates, edits, or retrieves such images. An agent cannot distinguish it from image_poster or image_create on this basis.

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 when-to-use, when-not-to-use, or alternative routing is given. With 29 siblings including image_create, image_poster, image_cutout, and image_enhance, the absence of any disambiguation guidance is a serious gap.

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

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the agent knows this is a mutating, externally-reaching operation. The description adds no behavioral context at all — nothing about processing time, URL requirements, or whether the original image is preserved or overwritten — so it fails to build on the annotation baseline.

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?

It is technically one sentence with zero waste, but the brevity is under-specification rather than conciseness — the single phrase conveys no actionable information for a seven-parameter tool. The low score reflects missing substance, not 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 seven-parameter, non-idempotent, external-facing mutation tool with no output schema, the description is completely inadequate. An agent has no way to know preconditions, async/callback behavior implied by callback_id and idempotency_key, or expected results.

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

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

Schema description coverage is 100% with all seven parameters individually labeled (scale, method, image_url, resolution, callback_id, workspace_id, idempotency_key). Per the baseline rule for high coverage, the schema carries the burden and the description is not required to compensate, so 3 is appropriate despite adding nothing.

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 "图片增强" merely restates the tool name image_enhance in Chinese, adding no scope, input expectation, or output meaning. It gives no basis for distinguishing this tool from siblings like image_create, image_cutout, or image_ecommerce beyond the obvious name reading.

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 whatsoever on when to use this tool, when to prefer an alternative such as image_create or video_enhance_v2, or what inputs are required. The agent is left to infer everything 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?

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds nothing on top — it does not explain the async callback behavior implied by callback_id/idempotency_key, expected latency, or what the erasure actually does to the source image.

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?

At four characters this is not conciseness but under-specification — there is no front-loaded information to structure. Brevity here removes value rather than tightening it.

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 10-parameter, non-read-only image generation tool with no output schema, the description should at minimum explain the mask/instruction workflow and the asynchronous result retrieval implied by callback_id. None of that is present, leaving the agent to infer the entire invocation contract from field names.

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% across all 10 parameters, so the schema itself documents each field; the baseline for a fully annotated schema is 3. The description contributes no additional meaning about how mask_url, instruction, or method interact, so it neither helps nor hurts.

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?

"AI 图片消除" is essentially a Chinese restatement of the tool name (image_magic_eraser) — an AI image erasure tool. It conveys a generic verb+resource but offers no detail about what is being erased (object removal? background? watermark?) and does not distinguish it from siblings like image_cutout or video_magic_eraser.

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 versus image_cutout, image_enhance, or the video counterpart. No prerequisites, required inputs, or exclusions are stated anywhere in the 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?

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the bar is lower, but the description adds no behavioral context whatsoever. It says nothing about the presence of a callback_id implying async execution, generation latency, rate limits, or whether reference images alter output — all relevant for a generative write 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?

It is short, but this is under-specification rather than conciseness — a four-character fragment carries no actionable content. There is nothing to be front-loaded because nothing is said.

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 9-parameter generative tool with an async callback parameter, no output schema, and zero explanation of input meaning or return behavior, the description is completely inadequate. An agent cannot determine what event_info should contain, what method values are valid, or 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?

The schema documents all 9 parameters (100% coverage), so the baseline of 3 applies even though the description adds no parameter detail. That said, the schema labels are themselves terse restatements ('海报生成方法' for method), so the description does not compensate with any semantics of its own.

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 bare noun phrase ('活动海报图') that essentially restates the tool name image_poster. It conveys the resource ('poster') but no verb or action, and it offers nothing to distinguish this from siblings like image_create, image_ecommerce, or image_enhance.

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 indication of when to use this tool versus the many other image_* siblings, nor any prerequisites or exclusions. The agent is given no routing information at all, leaving selection entirely to inference from the name.

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

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

Annotations declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the mutation and non-idempotent profile is partly covered. However, the description adds zero behavioral context of its own: it does not say whether creation is asynchronous, whether credits are consumed, what happens to the callback_id/webhook flow, or whether the persona is immediately usable.

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 short phrase with no wasted words, which is technically concise and front-loaded. But at six characters it is under-specified rather than efficient, so conciseness here reflects sparseness rather than disciplined editing.

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 non-idempotent, open-world creation tool with no output schema and only half its parameters documented, the description is far too thin. An agent gets no indication of expected inputs like photo_url, async job behavior, or how to track completion via callback_id.

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 only 50% — name and photo_url are undocumented in both the schema and the description, while callback_id and voice_audio_url carry their own schema descriptions. The description provides no parameter meaning at all, so it fails to compensate for the coverage gap.

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

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

"创建自定义 Persona" states a verb (create) and resource (custom Persona), but since the tool name is already persona_create, this is close to a restatement of the name. The qualifier "自定义" (custom) is the only added nuance, and it does nothing to distinguish the tool from siblings like persona_list or persona_delete beyond what the name already conveys.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as persona_list or get_persona_status. The description gives the agent nothing to decide whether this is the right tool at the right moment.

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

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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, and openWorldHint=false, so the safety and idempotency profile is covered. The description adds only the 'custom' qualifier and no new behavioral context such as confirmation requirements, authorization needs, or 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 a single front-loaded phrase with no filler, so it is structurally efficient. It is arguably too terse for a destructive operation, but it does not waste words.

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

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

For a one-parameter destructive tool, the description is incomplete: it omits parameter semantics, call prerequisites, and any usage guidance. The annotations cover the safety profile, but the undocumented actor_id and absence of when-to-use context leave real gaps.

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

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

Schema description coverage is 0%, and the description does not mention the actor_id parameter, how a persona is identified, or whether the parameter is required. It adds no meaning beyond the input schema's type declaration.

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 a specific verb (删除/delete) and resource (自定义 Persona/custom Persona), and the verb distinguishes it from siblings persona_create, persona_list, and get_persona_status. An agent can identify the action without opening the schema.

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 when-to-use guidance, prerequisites, or warning about irreversibility. It also does not contrast with any sibling, such as persona_list for inspecting personas instead of deleting them.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds useful context that results are scoped to the current user and paginated, but says nothing about ordering, result size, or page limits. With annotations carrying the safety burden, a 3 is fair.

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

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

Two short sentences, but the first ('个人创建演员列表') is essentially a title restating the second sentence, making it partly redundant. It is small enough not to be bloated, but not information-dense.

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 read-only paginated list with annotations covering safety, the definition is minimally adequate. However, with no output schema, it does not hint at return shape, item count, or pagination metadata an agent might need.

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 for individual parameters is 0%, so the description must compensate but only says '分页查询' (paginated query). It adds no meaning about limit/offset defaults, maximums, or behavior beyond what the schema-level description ('offset、limit 为分页参数') already states.

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 a specific verb and resource: '分页查询当前用户创建的个人演员（Persona）列表' – a paginated query of personas created by the current user. This clearly scopes the tool and implicitly contrasts it with the mutate siblings (persona_create, persona_delete). It stops short of explicitly naming any alternative sibling, so it lands at 4.

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 versus siblings like get_persona_status or persona_create/delete. Usage is only implied by the phrase '当前用户创建的' (owned by the current user). No exclusions, prerequisites, or alternatives are offered.

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

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, destructiveHint=false. The description adds nothing: it does not disclose that this is likely an async task (implied by the callback_id/webhook parameter), nor any auth, rate-limit, or lifecycle behavior. Zero added behavioral context.

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

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

It is short, but this is under-specification rather than conciseness. Four characters with no front-loaded task scope, constraints, or outcome leaves every sentence that should exist absent.

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 non-read-only, non-idempotent tool with a webhook callback parameter and no output schema, the description should explain the async task lifecycle, what the analysis produces, and how results are delivered. None of this is present, making it completely inadequate.

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% (video_url, callback_id, workspace_id all documented in the schema), so the schema carries parameter meaning. The description adds no additional parameter semantics, which matches the baseline 3 for a fully-covered 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?

"视频拉片" essentially restates the tool name video_analyze (video breakdown/frame-by-frame analysis). It names the resource but uses industry jargon and provides no differentiation from the many sibling video tools (video_edit, video_enhance_v2, video_translate, etc.). An agent cannot tell which video task this uniquely performs.

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 when-to-use guidance, no mention of alternatives, and no conditions or prerequisites. With 29 sibling tools, the agent is given nothing to route on.

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

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

Annotations already declare a non-read-only, open-world, non-idempotent task, but the description adds nothing: no mention of asynchronous job submission, callback/webhook delivery implied by callback_id, processing time, or failure modes. For a generation tool this is a complete disclosure gap, with no contradiction.

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

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

Four characters is not conciseness but under-specification; there is no front-loaded context or structure to evaluate, and the schema's duplicate "视频换脸任务。" adds nothing either.

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 4-parameter, open-world, non-idempotent video generation task with no output schema, the agent needs to know input formats, async/callback behavior, and constraints. None of this is present, so the definition is inadequate to invoke the tool correctly.

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

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

Schema description coverage is 50%: image_url and callback_id are documented in the schema, while video_url and workspace_id carry no description anywhere. The description supplies no parameter meaning at all, so it fails to compensate for the uncovered half.

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?

"视频换脸" is a direct restatement of the tool name video_character_swap rather than an independent explanation of what the tool does. It conveys the resource (face swap on video) but adds no scope, verb nuance, or sibling differentiation against the many other video_* tools.

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

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

There is no when-to-use, when-not-to-use, or alternative guidance. Nothing tells an agent how this differs from video_edit, video_magic_eraser, or video_generate, so selection must be inferred 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?

Annotations already declare mutation (readOnlyHint=false), openWorld, non-idempotent and non-destructive, so safety is covered. The description adds real value by disclosing the error condition (both/neither source fails) and the model lock. It still omits the async/webhook lifecycle (callback_id is a webhook trace id) and whether the operation is long-running or whether reference_images/ratio alter behavior, which matters for a media-mutation tool at this 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?

Terse and front-loaded: the purpose line comes first, then the constraints in short bullet-like lines with no filler. Some information is duplicated verbatim in the schema-level description, but the tool-level text itself is efficiently structured.

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

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

For a 10-parameter, zero-required, non-read-only media tool with no output schema and several undocumented parameters, the description is too thin. It omits the edit outcome, output/return handling, async completion behavior, and how the large set of remaining parameters interact, so an agent would have to guess on most calls.

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 only 20%, so the description must compensate, yet it explains roughly 3 of 10 parameters (model, workspace_id/video_url exclusion, mask_url). Prompt, ratio, resolution, callback_id, idempotency_key and reference_images carry no meaning in either place, leaving the majority of the surface undocumented.

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?

It names a resource ('视频' / video) and verb ('编辑' / edit) plus a key constraint (only seedance-2.0, source video via workspace_id XOR video_url), which is more than a bare tautology. However, it never says what the edit actually accomplishes (text-driven restyle? local repaint?) nor distinguishes itself from the many siblings (video_inpaint, video_magic_eraser, video_extend, video_enhance_v2). An agent cannot confidently route between these tools from this 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?

It gives a concrete invocation rule: pass exactly one of workspace_id/video_url, and it explains the optional mask_url enables local editing. That is useful conditional guidance for calling the tool. But there is no when-to-use-this-vs-alternatives guidance against the ~15 sibling video tools, and no prerequisites or ordering information.

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

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=false, so the basic safety profile is covered. The description adds zero behavioral context beyond that — it never mentions that this is an asynchronous job (implied by callback_id) or how idempotency_key affects retries, which the annotations alone cannot convey.

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?

It is extremely short, but this is under-specification rather than conciseness. There is no structure to evaluate — a four-character fragment cannot be front-loaded when nothing follows it.

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 7-parameter asynchronous video tool with no output schema, the description is completely inadequate. Nothing explains the async callback flow, the meaning of idempotency_key, valid enhancement methods, resolution options, or any duration limits.

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 is nominally the source of truth and the baseline is 3. However the schema descriptions are one-word labels ("增强方法", "输出分辨率") with no allowed values, and the tool description adds nothing to compensate — particularly for method and resolution, where no enum exists.

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?

"视频增强" merely restates the tool name (video_enhance_v2) with no additional specificity about what kind of enhancement, what input it accepts, or what it produces. It is a tautology rather than a description, and it does nothing to distinguish this tool from siblings like video_upscale, video_edit, or image_enhance.

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 whatsoever on when to use this tool versus alternatives. With roughly 30 sibling tools including video_upscale and video_edit, the absence of any routing condition leaves 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?

Annotations already declare the safety profile (not read-only, open-world, not idempotent, non-destructive). The description adds real value with the source-video mutual-exclusion rule and its error behavior, but says nothing about the asynchronous job/webhook delivery implied by callback_id and the get_work_status siblings, nor about what is produced.

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?

Four tight lines, front-loaded with the operation, then the model restriction, then the source rule and the duration semantics. No filler; each sentence carries a distinct constraint.

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 9-parameter async video tool with no output schema and no required parameters, the definition covers the critical input rules but omits return/delivery behavior (polling vs webhook via callback_id) and several optional parameters. Adequate to call correctly, not complete.

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 only 33%, so the description must compensate, and it does explain the workspace_id/video_url exclusivity, the incremental meaning of duration, and the model restriction. But ratio, prompt, callback_id, and idempotency_key remain unexplained in both the schema and the description.

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?

States a specific verb+resource plus scope: video extension by appending N seconds at the end of a source video. That is clearly distinct from video_generate (new video) or video_edit (modify existing), though no sibling is named explicitly.

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?

Gives useful preconditions — only the seedance-2.0 base, and the either/or rule for workspace_id vs video_url with both/neither being an error. However it never says when to choose this tool over alternatives such as video_generate or video_edit, so routing is left to inference.

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 annotations only covering safety/idempotency flags, the description adds genuinely new behavioral context: the task is async, results are delivered via webhook, and per-model limits are validated server-side rather than client-side. The one gap is that the async lifecycle details (task ID return, webhook payload) are only gestured at.

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

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

Three short lines, front-loaded with the generation modes followed by the async workflow and the model-variability caveat. Nothing is padded, though the terseness borders on under-specification for a 12-parameter 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?

For a 12-parameter, no-required-field, no-output-schema tool, the description covers the async lifecycle and model variability but omits concrete return handling — no mention of what the submit call returns (task ID?) or what the webhook payload contains — leaving the agent to infer the full round trip.

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 67% and the schema's own top-level table already documents the per-model duration/resolution/ratio/reference_* matrix in detail. The description only restates that these limits 'vary by model', so it adds little beyond the structured data — the 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 states a specific verb and resource (视频生成) and enumerates the generation modes it covers: text-to-video, image-to-video, first/last-frame, and multi-reference media. That distinguishes it reasonably well from editing/extending siblings like video_extend or video_edit, though no sibling is named explicitly.

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

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

It gives operational guidance — the call is asynchronous, status is polled via /openapi/v1/work/status, and the result arrives by webhook — which tells the agent how to consume the tool. However, it never states when to choose video_generate over alternatives such as video_extend, video_edit, or image_create.

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

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds nothing beyond that: it does not say whether this is an async job, that a task/callback flow is expected (despite callback_id and the get_work_status siblings), or what happens to the source video.

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?

It is a single short phrase with no wasted words, but it is under-specified rather than genuinely concise. There is no front-loaded scope, constraints, or output expectation.

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?

A video mutation tool with no output schema, no annotation-derived behavioral detail in the description, a 0-required-parameter schema, and a webhook/callback flow hinted at only by the schema field. An agent cannot determine inputs, job lifecycle, or how to retrieve results from this definition.

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 only 33% – only callback_id is documented in the schema, and video_url and workspace_id (including why 0 params are required) are unexplained anywhere. The one-line description provides zero parameter meaning to compensate for this gap.

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

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

The phrase "视频水印消除" names a specific verb+resource (remove watermarks from video), which is distinct from siblings like video_magic_eraser or video_subtitle. It is clear about what the tool does, but offers no explicit contrast with the other video-editing siblings.

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 when-to-use guidance, no prerequisites, and no named alternative. An agent must infer from the name alone that this is the watermark-removal option among many video tools.

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

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is partly covered. But the description adds nothing beyond that: it does not say the call is asynchronous/job-based, that a callback is needed for results, whether it consumes credits, or how long generation takes. With annotations doing the baseline work, the added value here is essentially nil.

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?

It is short, but this is under-specification rather than conciseness: one four-character phrase that mostly restates the tool name. There is no structure, no parameter mention, and no actionable content for an agent to act on.

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 generative, open-world, non-idempotent tool with four undocumented parameters, no output schema, and no async/callback semantics explained, the description is wholly inadequate. An agent cannot determine inputs, expected behavior, or result retrieval from what is provided.

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 only 25% — only callback_id is documented — so the description must carry the param burden and does not. It says nothing about what prompt, audio_url, or avatar_url should contain (formats, accepted hosts, size/duration limits, whether avatar_url is an image or video), despite these being the core inputs of a lip-sync task.

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 names a recognizable capability (video lip-sync), so the purpose is inferable from the name plus text. However, it gives no verb+resource phrasing and nothing that separates it from siblings like video_generate, ai_actor_say, or video_character_swap, which plausibly also produce talking-head video. Minimum viable but undifferentiated.

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 is a bare capability label with zero guidance: no when-to-use, no when-not-to-use, no prerequisites (e.g. that an avatar plus audio are needed), and no routing to alternatives among the 29 sibling tools. Nothing in the text helps an agent choose this tool over another.

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

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

Annotations declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, but the description adds nothing on top of them. It does not explain that this appears to be an asynchronous job (given callback_id/idempotency_key), how long erasure takes, or what happens to the source video. No contradiction with annotations, but no added value either.

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 phrase is brief, but this is under-specification rather than conciseness — there is no structure or front-loaded detail beyond a four-character label. Brevity here costs the agent all actionable information.

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

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

For a six-parameter asynchronous job submission tool with no output schema, the description is completely inadequate. It omits the async/callback nature, the meaning of method, the video source requirement, and any output expectations, leaving the agent unable to call it correctly.

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

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

Schema description coverage is 100% (method, duration, video_url, callback_id, workspace_id, idempotency_key are all documented in the schema), so the baseline of 3 applies. The description contributes nothing beyond the schema, notably no hint about valid values for 'method'.

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 four-character phrase 'AI 视频消除' (AI video erasure) essentially restates the tool name video_magic_eraser rather than describing what it does. It does imply a video-domain erase operation, but gives no detail on what is eliminated, from what, or how it differs from siblings like video_inpaint or image_magic_eraser.

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 whatsoever on when to use this tool versus video_inpaint, video_edit, or image_magic_eraser. No prerequisites, no exclusions, no context of any kind.

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 annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is partially covered by structured data. However, the description adds no behavioral context beyond those annotations—it does not explain what the tool creates or modifies, whether it needs auth, or how it behaves. It does not contradict annotations, but it contributes essentially nothing.

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 this brevity is under-specification rather than useful conciseness. For a tool with 9 parameters and no output schema, five characters of text do not earn their 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?

Given the tool's complexity (9 parameters, no required fields, no output schema) and the sparse schema descriptions, the definition is completely inadequate. An agent cannot determine what the tool does, when to call it, or how its parameters work from the description alone.

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 9 parameters with only 22% description coverage, leaving most parameters undocumented in both the schema and the description. The description provides no parameter-level meaning at all, so it fails to compensate for the low 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 '视频动作控制' is a noun phrase that restates the tool name rather than specifying an action, so it does not distinguish this tool from sibling video tools like video_generate, video_edit, or video_character_swap. It is a tautology, matching the calibration anchor for a score of 2.

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, what it is an alternative to, or what prerequisites it has. The description provides nothing beyond the name, so an agent cannot infer usage context from 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?

Annotations declare readOnlyHint=false and idempotentHint=false, implying a non-idempotent mutation, but the description does not explain that this is likely an asynchronous job (callback_id suggests webhooks) or how results are retrieved. It adds no behavioral context beyond the terse annotations, leaving the async/submission semantics entirely undisclosed.

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

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

Two words is technically brief, but this is under-specification rather than conciseness — there is nothing front-loaded because there is nothing to front-load. No sentence earns its place because no informative sentence exists.

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?

A 7-parameter, non-read-only tool with no output schema, no enums, and near-zero schema coverage needs the description to carry the burden; instead it says only "video subtitles". Nothing about required inputs, output retrieval, or async behavior is conveyed.

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 only 14%: just callback_id is documented (as a custom tracking ID). The description supplies no meaning for video_url, style_type, source_language, subtitle_format, or translate_language, so an agent must guess at formats, allowed values, and whether all are optional.

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?

"视频字幕" merely restates the tool name; the schema description "视频字幕任务。" adds nothing further. There is no verb (e.g. generate/burn-in/translate subtitles) and no differentiation from siblings like video_translate, video_analyze, or video_generate.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as video_translate despite subtitling and translation being closely related operations. The agent gets no basis for choosing this tool over its siblings.

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

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, covering the safety profile. However, the description adds nothing: it does not disclose that this is likely an asynchronous task requiring a webhook (implied by callback_id), nor expected processing behavior. With annotations present, the bar is lower, but the description contributes zero additional behavioral context.

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

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

The description is a single four-character phrase with no front-loaded explanation or structure. Brevity here reflects under-specification rather than earned conciseness, since essential information is entirely absent.

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 4-parameter, presumably asynchronous video translation task with no output schema and no annotations explaining the workflow, the description is completely inadequate. It fails to explain the required inputs, the callback/webhook mechanism, or expected output, leaving the agent unable to call 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 only 50% – video_url and workspace_id have no schema descriptions, and target_lang's description is just "目标语言". The tool description does not compensate for any of these gaps, merely duplicating the schema description "视频翻译任务" in spirit without clarifying parameter roles.

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 "视频翻译" simply restates the tool name and adds no verb+resource specificity beyond what the name already conveys. It does not distinguish this tool from siblings like video_subtitle or video_generate, so an agent learns nothing new.

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 versus alternatives such as video_subtitle (which presumably also handles language), nor any mention of prerequisites or input constraints. The description offers no usage context at all.

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

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered by structured data. The description adds nothing beyond that — it never says the job is asynchronous, that a task/workflow ID is returned, or that progress is polled via get_work_status, despite callback_id hinting at that model.

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?

At four characters the text is not concise, it is under-specified. There is no front-loaded statement of what the tool produces or how to invoke it, so brevity here costs the agent essential information.

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

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

No output schema exists and the description supplies nothing about return values, task status handling, or async polling. Combined with only 33% parameter coverage and zero usage guidance, the definition is far too thin for a three-parameter media-processing tool with siblings like video_enhance_v2 and get_work_status.

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 only 33% (just callback_id), and video_url and workspace_id have no descriptions in either the schema or the description text. Nothing in the description explains accepted URL forms, video size/duration limits for upscaling, or how workspace_id scopes the job.

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?

"视频超分" (video super-resolution) does name the operation, but it essentially restates the tool name video_upscale as a noun phrase rather than stating a verb plus scope. It gives no differentiation from the close sibling video_enhance_v2, which plausibly also improves video quality, so an agent cannot tell the two apart from the description alone.

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 usage guidance of any kind: no when-to-use, no when-not-to-use, no mention of video_enhance_v2 as an alternative, and no prerequisites. The agent is left to guess 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.