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

No annotations, so the description carries the full burden and does well: it discloses the consistency guarantee, text truncation at 200 chars (~45s), the actor-not-found error behavior routing to create_actor, and the return format (24 kHz mono WAV path). It does not mention latency, cost, or concurrency, which keeps it short of a 5.

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?

Front-loaded with purpose and the key routing decision, then parameters and return value in clearly delineated sections. Every line earns its place; no filler.

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

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

Output schema exists, so return-value detail is optional (though provided). With no annotations and 0% schema coverage, the description successfully covers purpose, routing, all params, error behavior, and output format. Minor gaps around speaking_rate/seed ranges and operational limits prevent a 5.

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

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

Schema coverage is 0%, so the description must document params and it does all four: actor (name from create_actor), text (200-char cap, truncation), speaking_rate (rate multiplier), seed (random seed). The last two are thin — no valid ranges — so it compensates well but not exhaustively.

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 ('make an already-cast actor speak a line') and a distinctive property (timbre consistency across every line). It explicitly names and contrasts with the sibling generate_speech, so an agent can distinguish it without opening any 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?

Gives explicit when-to-use ('game NPC dialogue'), when-not ('don't use generate_speech — its timbre drifts per line'), and a prerequisite path (if the actor doesn't exist, it tells you to create_actor first). Alternatives and conditions are fully specified.

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?

无 annotations，描述承担行为说明责任；它说明了状态涵盖引擎、能力和资产位置，并主动解释“工具不存在”可能是被安装脚本关闭而非故障。这提供了有用诊断上下文，但未明说只读/无副作用等安全属性。

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?

两句话，先总述状态内容，再给出故障排查指引；信息前置，无冗余，每句都有明确作用。

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?

存在输出 schema，因此无需描述返回值；工具无参数且用途简单。描述已覆盖状态范围与关键使用场景，信息完整。

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?

该工具无参数，输入 schema 为空且覆盖率为 100%。无参数工具的参数语义基线为 4，描述无需补充参数含义。

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?

明确说明这是本插件当前状态工具，并列出返回内容：两个引擎是否存在、哪些能力启用、资产存放位置。它与所有创建/生成/导入类兄弟工具在用途上明显不同，代理可据此区分。

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?

给出明确使用时机：当某个工具“不存在”时先查这里；还解释了常见原因（显存不足导致生图能力被安装脚本关闭）。但没有列出何时不用或替代工具，故非满分。

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 and does well: it discloses the output (a local path to the audition clip) and the consequential side effect of force=true (previously generated lines no longer match). It stops short of stating what happens if name already exists without force (error vs. reuse), so one behavioral gap remains.

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 purpose sentence and the parameter block are front-loaded and tight. The middle 'why' paragraph justifies the tool's existence but spends several sentences on 125 Hz/242 Hz/5 Hz measurements, which is more evidence than an agent needs to make a selection decision.

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?

An output schema exists, so return values need not be explained in prose (the description still notes the audition path usefully). For a 5-parameter mutation tool with zero schema coverage and no annotations, the description supplies the operational context needed to invoke it correctly.

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

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

Schema description coverage is 0%, so the description must compensate entirely – and it does. All five parameters are explained: name with charset/length constraints, voice with a concrete English example and content guidance, sample_text with its default, seed, and force with its destructive consequence.

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 ('给一个角色铸声(定妆)' – mint/cast a voice for a character) and immediately distinguishes itself from the sibling it feeds into ('之后用 actor_tts 让他说任意台词'). An agent can tell this apart from actor_tts, import_actor, or generate_speech without opening a 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?

Clearly states when to use it: before actor_tts, to lock a stable timbre, and force=true to re-cast. It gives a clear workflow position but doesn't name alternative casting routes (import_actor, create_character) or say when those would be preferred instead.

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 burden and does well: it explains that appearance values are hardcoded defaults that can be overridden in scene (for removable gear and clothing), and that force=true triggers a re-design. It omits persistence/side-effect details (does this register a reusable subject that list_subjects/subject_image later reference?) and does not mention deterministic seeding 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?

Front-loaded with the purpose, then an efficient bulleted list of required appearance fields, then the override rule and the force workflow. Every line contributes, though the removable-gear/clothing aside adds slight 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?

An output schema exists, so return values need not be described, and the appearance/override/force semantics are well covered. Gaps remain around the image-generation parameters and whether the created animal becomes a reusable referenced subject, but the core workflow is 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 0%, so the description must compensate. It thoroughly explains 'appearance' (exactly which attributes to specify) and 'force', but leaves seed, width, height, guidance_scale, and num_inference_steps entirely undocumented in both schema and description. Partial compensation warrants a 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 a specific action (create/lock the design of an animal, mount, or spirit beast) and the concrete outcome (every subsequent image shows the same creature), which is a distinct purpose from the animal/character/object siblings. An agent can tell this is the animal-design tool 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?

It gives clear workflow guidance: design first, inspect the resulting design image, and rerun with force=true if unsatisfied. It also implicitly scopes out scene/action content ('不要写场景和动作'). It stops short of explicitly naming which sibling to use for scenes or characters, so not a full 5.

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 and largely meets it: it discloses that this persists a locked-in appearance that governs all future subject_image output, that a bad result locks the whole character into the wrong look, and that force=true is the re-roll escape hatch, plus an instruction to verify the returned reference image. It is silent on the non-appearance generation knobs (seed, guidance_scale, steps, size) and on collision behavior when a name already exists.

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?

Well front-loaded – the one-line purpose precedes the rationale and the field guidance – and structured into clearly labeled sub-sections that an agent can scan. It is on the long side, and the illustrative anecdote about the robe-to-armor swap could be trimmed, but essentially every sentence carries usable instruction.

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?

An output schema exists, so return-value explanation is not owed, and the description correctly just tells the agent to inspect the returned reference image. Combined with the purpose, usage and appearance guidance, an agent can call this correctly; the gaps are the undocumented generation parameters and name-collision behavior rather than anything blocking.

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

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

Schema coverage is 0%, so the description must compensate. It does so richly for the two most important parameters: `appearance` is decomposed into identity vs. default clothing with a concrete list of what must be pinned down, and `force` is defined as the re-create/override switch. The other five parameters (seed, width, height, guidance_scale, num_inference_steps) receive no semantics at all, leaving a substantial documentation hole.

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 sentence names a specific verb and resource ('给一个人物定妆' – generate and persist a character reference) and immediately contrasts it with generate_image and subject_image, so the agent knows it is not a one-off image generator. It does not, however, differentiate itself from the parallel siblings create_actor / create_animal / create_object, which is the one ambiguity left.

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

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

Explicit about when to use it (whenever a character must stay visually consistent across many images), what to use instead for one-offs (generate_image), and what NOT to put in this call ('不要写场景、动作、表情' – leave those to subject_image's scene). It even gives a worked example of swapping clothing via scene without re-creating the character, which is exactly the when/when-not guidance an agent 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 carries full burden. It does disclose a real behavioral trait: consistency of the object across images and angles, and that geometry drifts most. It also mentions rerolling with force. But it omits key mechanics: whether this is persistent/long-lived (only 'continuity_status' hints at that), idempotency, cost, or that seed/guidance_scale/steps control determinism.

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 appearance checklist is genuinely useful and front-loaded, and the scene/angle exclusion is a strong, earned sentence. But the opening anecdote about the treasure chest lid is long and the overall text is padded; it leans more persuasion than spec. Structure is reasonable but not tight.

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?

An output schema exists, so return-value explanation isn't required. For an 8-param generation tool with no annotations, the description focuses almost entirely on the appearance field and lacks behavioral detail on persistence, determinism, and the many unlabeled generation parameters. Adequate for the creative how-to but thin as a full tool contract.

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% across 8 parameters, so the description must compensate. It only meaningfully covers 'appearance' (extensively, with required content), and touches 'force' for rerolls. It says nothing about name, seed, width, height, guidance_scale, or num_inference_steps — six of eight parameters unexplained in both schema and 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?

The description describes the goal in domain-specific terms ('定妆' = locking in a canonical look for a prop/object so every subsequent image matches it), which clarifies the purpose as creating a persistent object reference. However, it never explicitly states it is the object-creation tool relative to siblings like create_character or create_animal, and the framing is heavily tutorial-flavored rather than naming the operation. The intent is inferable but not crisply 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?

It gives strong guidance on WHAT to put in appearance and what to exclude ('不要写场景和角度 —— 角度留给 subject_image 的 scene'), effectively routing scene/angle work to a sibling. But it gives no guidance on when to use this tool vs. create_character/create_animal, no prerequisites, and the 'force=true' reroll note is the only invocation condition described.

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

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

With no annotations provided, the description carries the full disclosure burden and does so well: it explicitly warns that the operation is irreversible (不可逆) and explains the concrete consequence that the reference voice cannot be reproduced and a re-created actor would be a different person. It omits permission/auth requirements, but the destructive consequence is unusually well articulated.

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 clauses, front-loaded with the action and immediately followed by the risk. Every word earns its place with no redundancy.

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

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

An output schema exists, so return values need not be described. For a destructive single-parameter tool with no annotations, the description adequately covers purpose, irreversibility and consequence; the main gap is any guidance on how to identify the actor via the name parameter.

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 one required parameter (name) with 0% schema description coverage, and the description adds no information about it whatsoever – no format, matching rule, or identifier guidance. With coverage this low the description should compensate and does not.

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 (删掉/delete) and a qualified resource (一个已铸声的角色 – a voice-cast actor), which is more precise than a bare 'delete actor'. It does not explicitly distinguish itself from the sibling delete_subject, 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 statement of when to use this tool versus alternatives such as delete_subject or list_actors, and no preconditions for invoking it. The agent must infer usage from the verb 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, so the description carries the full burden, and it does disclose the key destructive trait: the operation is irreversible and the finalized image cannot be reproduced, so re-finalizing yields a different subject. It omits confirmation requirements, permission needs, and whether dependent assets (images, sheets) are also removed.

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, no filler, with the destructive/irreversibility warning front-loaded right after the action statement. Every clause 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?

An output schema exists so return values need not be explained, and the irreversibility warning covers the most important behavior. However, for a destructive tool with no annotations and no parameter documentation, the description should say more about what else is destroyed and how it relates to delete_actor.

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% for the single 'name' parameter, and the description adds nothing about it — it never clarifies whether 'name' is a subject name, an ID, or whether it must match exactly. For a destructive identifier parameter, leaving it undocumented is a real 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?

States a specific verb (删掉/delete) and resource (一个已定妆的角色或物件 – a finalized character or object), with scope that implicitly distinguishes it from delete_actor by covering subjects of both kinds. Sibling differentiation is only implicit, though; it never names delete_actor or explains why a 'subject' differs from an 'actor'.

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 qualifier '已定妆的' implies a precondition (only subjects whose look has been finalized) and '重定出来是另一个' hints that re-creation is an option, but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as delete_actor. Usage must be inferred.

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 and does well: it discloses the non-deterministic/one-off nature of the output, that reference_image_path switches to image-to-image mode, and the speed/quality tradeoffs of num_inference_steps and guidance_scale. It stops short of covering permission needs, rate limits, cost, or resolution failure modes, which keeps it from a 5.

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?

Front-loads the defining distinction, then the sibling routing, then a compact parameter list, then the return value. Given the 0% schema coverage the parameter section is earned, and there is no filler.

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

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

Despite having no annotations and a 7-param schema with no descriptions, the definition covers scope, alternatives, per-parameter semantics, and even the return value (a local path). An output schema exists, so return details are not strictly required, making this fully sufficient for correct invocation.

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

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

Schema description coverage is 0%, so the description must compensate and it does: every one of the 7 parameters is explained with meaning beyond type, including the 1024 cap on width/height, the optional seed, the img2img behavior triggered by reference_image_path, and the quality/latency and adherence/artifact tradeoffs of the two sampling params.

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 and resource (生成一张一次性图片) and immediately defines the key scope constraint: the output is not guaranteed consistent with any other image. It explicitly distinguishes itself from create_character, create_object, and subject_image, so an agent can route correctly without opening any 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?

Gives both when-not and when-to-use: recurring characters/objects should go to create_character/create_object then subject_image, while this tool is for backgrounds, UI base images, and other one-off assets. The alternative is named with the condition that selects it, leaving nothing 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?

No annotations are provided, so the description carries the full behavioral disclosure burden. It usefully reports that the tool returns a local WAV path, that the output is not seamlessly loopable, that duration is capped at 120 seconds, and that higher inference steps are slower. It does not cover permissions, rate limits, or failure modes, but the core behavioral constraints an agent needs are present.

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 front-loaded with the purpose, then presents parameters in a compact list, and finishes with an important output caveat. Every part earns its place given the lack of schema descriptions, and there is no wasteful repetition.

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

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

Although an output schema exists, the description still helpfully notes the returned WAV path. With no annotations and 0% schema parameter coverage, the definition compensates by documenting all parameters and the key output limitation. It is complete enough for an agent to select and invoke the tool correctly.

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

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

Schema description coverage is 0%, so the description must explain all four parameters. It does so clearly: prompt is a music description with English working best, seed is optional random, duration is seconds with a 120 upper bound, and num_inference_steps defaults to 100 with more steps being slower. This adds meaning beyond the bare schema types and defaults.

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

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

The description states a specific verb and resource: '生成一段背景音乐(Stable Audio), 返回 WAV 的本机路径'. It clearly distinguishes itself from generating speech or sound effects by specifying background music, though it does not explicitly name sibling alternatives such as gen_sfx or generate_speech.

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 an important usage caveat: the output has a beginning and end with no seamless loop point, so for looping BGM the user must find a loop point or treat it as one-shot transition music. However, it does not explicitly state when to use this tool versus generate_speech, gen_sfx, or other audio-generation 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?

With no annotations, the description carries the full behavioral burden and does disclose key traits: no cross-sentence voice consistency, a default neutral narration voice when `voice` is omitted, a 200-character cap, and the output format (24 kHz mono WAV, local path). It does not mention determinism, cost, or latency, so it stops short of exhaustive, but the critical gotcha (voice instability) is stated up front.

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?

Front-loads the differentiating constraint before any parameter detail, then uses a clean parameter block and a one-line return note. The extra sentence reinforcing the 'second line' rule is slight redundancy but functions as a strong routing heuristic, so it earns most of its space.

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 generation tool with no annotations and a rich sibling set, the description supplies the routing rule, the character-limit constraint, default behavior, and output artifact. With an output schema present it did not need to describe the return, yet the one-line WAV note costs little and removes ambiguity.

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%, so the description must compensate, and it largely does: `text` gets a 200-character limit, `voice` is explained as a natural-language description with English working best and a documented default, and both are the semantically important ones. `seed` and `speaking_rate` are only labeled '可选' with no explanation of what seed controls, leaving a partial 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?

States a specific verb and resource (one-shot narration generation) and immediately scopes it: '一次性旁白 —— 不保证跨句音色一致'. It explicitly names the sibling route (create_actor + actor_tts) that handles the case it does not cover, so an agent can distinguish it from the voice/actor tools without opening any 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?

Gives both a positive use case (system prompts, one-off announcements, '说完就没了' audio) and an explicit exclusion ('任何会说第二句的角色都不该用这个'), plus the concrete alternative to use instead. This is exactly the when/when-not/alternative structure.

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 and does well: it discloses millisecond-level latency, byte-identical reproducibility under a fixed seed, no model/VRAM usage, and the exact output format (44.1kHz 16bit mono WAV path). It stops short of stating file-write/overwrite behavior or where artifacts land, so not a 5.

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?

Front-loaded with purpose then contrast, then a clean params/return block; every section earns its place. Minor redundancy in reiterating seed reproducibility ('同 seed 结果完全相同' and '同 seed 逐字节可复现'), but overall tight and well organized.

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 5 params with zero schema coverage, a nested overrides object, an existing output schema, and no annotations, the description is complete enough for correct invocation: all inputs are explained, the output artifact and its structured params are described, and reproducibility semantics are 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?

Schema coverage is 0%, so the description must compensate and it does: it enumerates preset and wave values, explains seed semantics precisely (jitter around the preset's parameters, not sample points; identical seed yields identical output), defines base_freq incl. its meaning under noise, and points to sfx_presets() for valid overrides keys with a worked example.

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 and resource (synthesize a programmatic sfxr/jsfxr-style game sound effect) and immediately distinguishes itself from the sibling generate_music. An agent can tell exactly what it produces and what it does not.

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

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

Explicitly names the alternative (generate_music) and the condition that rules it out: diffusion music is tens-of-seconds broadband mush, whereas game SFX are 10~200ms transients needing precision and immediacy. This is textbook when-to-use/when-not 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?

由于未提供 annotations，描述承担了全部说明责任，且完成得非常好：它详细说明了音频格式约束（16 位 PCM WAV、2–30 秒、尽可能为干净的单人无伴奏人声）、自动转换行为（转为 24 kHz 单声道）、ffmpeg 回退命令、自动转录标注质量警告、force 覆盖行为以及同意/授权注意事项。这远超 schema 和 annotations 所包含的信息。

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?

开篇一句话简洁地前载了核心目的，随后用带标签的段落解释参数和注意事项。篇幅合理，每句话都提供了有用信息，但 ffmpeg 命令和转录警告略长。

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?

对于一个包含 4 个参数、无 annotations、0% schema 描述覆盖率的变更工具，描述提供了智能体正确调用所需的一切：用途、与兄弟工具的关系、每个参数的含义、输入格式要求、自动转换行为，以及授权注意事项。由于存在 output schema，无需再解释返回值。

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%，因此描述必须弥补这一差距；它确实做到了，为全部四个参数提供了含义：name（供 actor_tts 引用）、audio_path（本地路径及格式和时长规格）、transcript（用于克隆模型对齐，自动生成内容会被标记供审查）和 force（覆盖已有角色）。这已远超 schema 中裸属性名称所提供的内容。

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?

明确说明了动作（从一段现成录音铸造声音）和资源（角色），并直接说明它与 create_actor 的区别——唯一区别在于参考音频是由用户提供而非系统生成。这使智能体无需查看任一 schema 即可将其与同名资源类兄弟工具区分开来。

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?

清楚地说明了后续流程（actor_tts 稍后通过名称引用该角色），并给出何时提供 transcript 与让系统自动听写的条件。缺少与 import_subject 等同类导入工具的明确对比，但对于何时使用此工具已足够清晰。

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, and it delivers real behavioral detail: images over 1024 are downscaled, alpha channels are converted to RGB (transparency becomes black), and force overwrites an existing subject. It also warns that a scene-containing reference will replicate that scene. Missing permission/auth or failure-mode disclosure keeps it from a 5.

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?

Front-loaded with the one-line purpose before dropping into a structured 参数 list, and each parameter note earns its place with actionable detail. Slightly long, but the length is justified by the 0% schema coverage it has to make up for.

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 mutation tool with no annotations, the description covers overwrite semantics, image preprocessing, and reference-image constraints; the existence of an output schema means return values need not be explained. Auth/permission requirements and error behavior remain unstated.

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%, so the description must compensate, and it documents every one of the five parameters: name (used later by subject_image), image_path (with concrete requirements: single subject, front or 3/4 view, clean background, fully visible), appearance (required, injected into every subsequent scene prompt, with a warning about drift if omitted), kind, and force.

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 action (import a ready-made image to define a subject's look) and explicitly distinguishes it from siblings: the result is identical to create_character/create_object, only the reference image is user-supplied. An agent can tell it apart from create_character without opening either 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?

Explains the workflow context clearly: use this when you already have a reference image, then subject_image generates arbitrary scene images whose appearance derives from that image. The comparison to create_character/create_object implicitly covers the alternative, though it never states an explicit when-not-to-use rule.

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. '列出' implies a read-only, non-mutating operation, and the parenthetical clarifies the returned content, but there is no mention of ordering, pagination, permissions, or what an empty result means. Adequate but thin for a tool with zero annotation coverage.

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 single front-loaded sentence with no filler. It's efficient, though the parenthetical return-field list is somewhat redundant given an output schema 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?

For a parameterless read tool with an output schema, the description supplies enough for correct invocation: it identifies the resource and the data returned. Only the lack of any routing hint against sibling list tools keeps it from a 5.

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 takes zero parameters, so the baseline is 4. The description correctly adds nothing about inputs, which is appropriate here.

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

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

The description uses a specific verb (列出/list) with a scoped resource (已铸声的角色 – characters that have had voices cast) and even enumerates the returned fields. It's clearly distinguishable from create_actor/delete_actor, but it does not explicitly differentiate itself from the nearby list_subjects sibling.

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 prerequisites, and no reference to alternatives such as list_subjects or actor_tts. Usage is only inferable from the verb 'list', which is weak for a tool with this many 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?

No annotations are provided, so the description carries the full burden. The verb 列出 implies a read-only list operation, which gives basic safety context, but it does not disclose pagination, return size, or other behavioral details.

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 single compact sentence that front-loads the core action and scope with no wasted words.

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

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

For a zero-parameter list tool with an output schema, the description is nearly complete: it names the resource and the finalized-only scope. A brief note on how it relates to sibling listing tools would close the remaining 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?

The tool has zero parameters, so per the rubric the baseline is 4. The description does not need to compensate for any 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 states a specific verb (列出) and resource (角色、动物和物件), and the qualifier 已定妆 narrows the scope. It is clear enough to distinguish from generic subject listing, but it does not explicitly contrast itself with siblings such as list_actors.

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

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

Usage is implied: the tool lists finalized characters, animals, and objects. There is no explicit when-to-use guidance, no exclusions, and no mention of alternatives like list_actors for unfinalized actors.

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 behavioral burden. It does an excellent job: it explains what the checkerboard artifact is, details mode-specific behaviors (auto detection heuristics, forced checker, forced rembg), documents quality trade-offs (speed vs. memory), and discloses return format plus warning conditions for bad results. Minor gap: it doesn't state whether the operation is idempotent or what happens if both image_path and image_base64 are provided.

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

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

The description is front-loaded with the core purpose and rationale before diving into parameters. It is thorough but not padded; every section earns its place. The only minor deduction is that the Chinese formatting and emoji might slightly increase parsing overhead for an agent, though the structure is logical and easy to scan.

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

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

Despite having no annotations and 0% schema description coverage, the description covers everything an agent needs: purpose, usage context, all parameters with semantics, return format (even though an output schema exists, the description adds warning conditions not captured there), and failure modes. An agent can call this tool correctly without opening 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?

Schema description coverage is 0%, so the description must compensate. It fully documents all four parameters: image_path (local path accepted directly from other tools), image_base64 (alternative input), mode (three valid values with exact behavioral definitions), and quality (two values with model names, runtime, and peak memory, plus note on default behavior based on system memory). This is exemplary compensation for missing schema descriptions.

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

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

The description states a specific verb and resource (remove image background, output real RGBA PNG with alpha) and explains the motivating scenario (generative models paint checkerboards as opaque pixels). It clearly distinguishes itself from siblings like generate_image or slice_sheet, which do not perform background removal.

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

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

The description clearly indicates when to use it ('做游戏精灵图必须用本工具把它转成真的 RGBA') and explains the mode selection logic. It does not explicitly state when NOT to use the tool, but the context is clear enough for correct invocation.

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

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

With no annotations the description carries the full burden and does disclose useful traits: exact field-name sensitivity that causes hard failure in gen_sfx, the fact that valid field names cannot be inferred, and the shape of the return (preset list, defaults table, sample rate). It is a read-only listing so auth/rate-limit disclosure is not critical, but no explicit statement of read-only safety is given.

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?

Front-loads the purpose, then the reason to use it, then the return contents. The parenthetical naming examples look verbose but each one illustrates a real ambiguity risk, so every sentence 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?

For a zero-parameter discovery tool with an output schema present, the definition is complete: it explains what to consult it for, why it matters, and sums up the return contents. Nothing an agent needs to call it or act on the result is missing.

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

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

Zero input parameters, so the baseline is 4. The description additionally explains what the returned field table means and gives examples of ambiguous field names (duty_sweep vs duty_slide, lpf vs cutoff), adding interpretive value beyond the empty schema.

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

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

States a specific verb (list) and resource (presets usable by gen_sfx), and goes further by naming the overrides fields and their defaults as part of the payload. It is clearly distinguishable from the sibling gen_sfx: this is the discovery/companion tool the agent consults before invoking gen_sfx.

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 explicit routing ('先看这里再去 overrides' – look here before touching overrides) tied to a concrete failure mode (wrong field names make gen_sfx fail). It identifies the sibling gen_sfx as the downstream consumer and the reason guessing field names is unsafe.

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, and it does useful work: it discloses the trim default (True), the mutual-exclusivity rule between rows/cols and frame_width/frame_height, and the fact that slicing writes per-frame PNG files to local paths. It does not discuss overwrite behavior or permissions, but the essential write semantics are visible.

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?

Front-loaded with the verb+resource, then the rationale, then a compact parameter block and the return value. Every segment earns its place; only the deferral of image input semantics to other tools is slightly loose.

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?

An output schema exists so return values need not be spelled out, yet the description still names the return shape (local PNG paths). With no annotations and zero schema descriptions, the description supplies the constraints an agent needs to choose between the two sizing modes, making it adequately 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 0% and all 7 params are bare titles, so the description must compensate and largely does: it documents the two image-input alternatives, the rows/cols pair, the frame_width/frame_height alternative, the trim flag with its default, and the exclusivity constraint that the schema cannot express. Only the image_path vs image_base64 distinction is deferred to 'same as other image tools'.

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 and resource ('把排成网格的 sprite sheet 切成单帧 PNG') and even explains the motivating case (image models laying out 2x2 grids instead of separate frames). No sibling tool covers sheet slicing, so the distinction is unambiguous.

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

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

Gives a concrete trigger ('让生图模型画"4 帧动画"时它会摆成 2x2 网格而不是 4 张图, 用本工具切开'), which tells the agent exactly when this tool applies. It stops short of naming alternatives or stating 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 carries the full burden and does well: it discloses the missing-subject failure path, the 1024 dimension cap, that unspecified seed/steps/guidance fall back to engine defaults, and the slower-but-finer tradeoff of more steps. It does not cover output file format, overwrite behavior, or reproducibility guarantees, so it falls short of a 5.

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?

Purpose and the sibling warning are front-loaded in the first two lines, followed by a clean parameter block. Every sentence earns its place — the dress/face example in particular prevents a common misuse without padding.

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?

An output schema exists, so the return value needs no elaboration beyond the one-line note that it yields a local path. Across a 7-parameter, 2-required generation tool, the description covers invocation, prerequisites, dimension limits, optional-parameter defaults, and identity/scene separation — nothing an agent needs is missing.

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%, so the description must compensate, and it documents all seven parameters. Critically it adds semantics the schema cannot: scene controls action/place/angle only while identity comes from the dated 定妆 image, and clothing can be swapped via scene text ('wearing heavy red armor') while preserving the face. That is genuine 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?

Specific verb+resource (出一张新图 of a 已定妆 character/object) plus the scope constraint that appearance must stay consistent with every prior image. It is immediately distinguishable from the sibling generate_image. No ambiguity about what the tool produces.

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

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

Explicitly routes the agent: use this for game assets 不要用 generate_image, with the reason (generate_image mutates the face each time). It also states the prerequisite path — if subject doesn't exist, go to create_character/create_animal/create_object first. Both when-to-use and the alternative are named.

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 burden well: it discloses auto-invocation by import_actor, that the model has built-in language identification, and the real-world failure mode (clone models dropping sentence tails) that motivates verification. It stops short of stating cost/latency or error behavior, so not a full 5.

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?

Front-loads the core behavior, then uses clearly sectioned blocks for uses and parameters. The script-verification rationale is slightly verbose but each sentence contributes useful context, so only marginally over-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?

An output schema exists, so return values need not be explained. Purpose, both parameters with constraints, and both usage modes are covered, leaving nothing an agent needs in order to call this 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 0%, so the description must compensate and does: audio_path is a local path restricted to WAV, and language is an optional hint (zh/en) whose default is model self-detection, with guidance to supply it only when a dialect is misclassified. This adds meaning well beyond the bare 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?

States a specific verb+resource+output: listen to a recording and return the spoken text as words. It also distinguishes itself from siblings by clarifying it is for verification, not subtitle production, and that import_actor invokes it automatically.

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?

Enumerates two concrete when-to-use scenarios (checking reference audio during import, validating a dubbed line against its script text) and explicitly excludes the wrong use case ('核对' not '生产字幕'). It also names how it relates to import_actor's automatic invocation.

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