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

No annotations are supplied, so the description carries the full behavioral burden and it is thin for a mutation tool. It does not say whether the draft must be open first, whether the change is reversible, whether saving is required afterwards, how duration behaves when omitted, or what the response looks like. The only behavioral content is track routing, which already appears in the schema.

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

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

Two front-loaded sentences with the core action and track routing first. The second sentence largely restates the schema's track description, a small redundancy, but overall it is tight with no 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?

This is a 9-parameter mutating tool with no annotations and no output schema, and the description leaves key agent questions unanswered: draft-open prerequisite, save requirement, duration defaults, and failure modes. The rich schema compensates on parameter semantics but not on behavior or workflow position.

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% and every parameter, including duration-string formats and volume ranges, is documented in the schema. The description adds no parameter meaning beyond what is already there, so the baseline of 3 applies.

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

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

The description opens with a specific verb and resource ('Add an audio clip') and enumerates the usable audio types (BGM, voiceover, sound effect), which clearly separates it from jianying_add_video, jianying_add_text, and jianying_add_subtitles. It does not name a sibling or state exclusions, so it stops short of 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?

'Use track 0 for the main audio bed and track 1 for narration' gives real routing guidance for one parameter, which is implied usage rather than when-to-use-vs-alternatives guidance. Nothing tells the agent when this tool is the right choice over another add_* sibling, nor what prerequisites apply.

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 present, the description does real work by disclosing the line-splitting heuristic (~18 chars/line) and even time distribution, plus that the generated lines are returned. However, it never says whether this replaces existing captions on the track, whether an open draft is required, or whether the operation is reversible – meaningful gaps for a mutation 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?

Three tight sentences with the core action front-loaded and the proofreading return value last. No filler or restatement of the 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?

Adequate for the core script-to-subtitles behavior, and the return value is mentioned. But for a 7-parameter tool with nested style objects and no annotations or output schema, it omits the track targeting semantics (0 vs 1) and overwrite behavior, which an agent needs before calling.

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

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

Schema coverage is 100%, so baseline is 3, but the description adds cross-parameter semantics the schema cannot express: how script, start, duration, and maxChars interact to produce evenly distributed lines. It still says nothing about how style or track affect the result in prose.

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 ("Add a full subtitle track from a script") plus the mechanics of splitting and distributing. It is clearly distinguishable from jianying_add_text and jianying_export_srt by implication, but 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?

Usage is implied by the phrase "full subtitle track" and by the note that generated lines are returned for proofreading, which hints at the script-to-captions workflow. There is no explicit guidance on when to prefer this over jianying_add_text or jianying_export_srt, and no stated prerequisites (e.g. draft must be open).

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 burden. It does not say whether the draft must be open first, whether the change is persisted or requires jianying_save_draft, whether it returns a segment identifier, or what happens when segments overlap on the same track. For a mutation tool with zero annotation coverage this is a substantial gap.

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

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

Two sentences, zero waste, with the core action front-loaded and the use cases following immediately. Nothing is padded or repeated.

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 mutation tool with a nested style object and no output schema deserves more than this: the draft-lifecycle context (open/save) and the return value are unaddressed. The rich schema covers the input surface well, which keeps it at minimum viable rather than 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%, including nested style fields, the enum for align, and the meaning of the track index (0 = captions, 1 = titles/overlays). The description adds almost no parameter-level meaning, so 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?

Specific verb and resource ('Add a text or subtitle segment to the text track') plus concrete use cases (titles, lower thirds, single captions). The word 'single' implicitly separates it from the sibling jianying_add_subtitles, but the sibling is never named so the distinction must be inferred.

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?

'Use for titles, lower thirds and single captions' gives an implied usage context and hints that bulk captioning belongs elsewhere. It never names jianying_add_subtitles as the alternative, and it does not state the prerequisite that a draft must already be open (the sibling jianying_open_draft exists).

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 behavioral disclosure burden. It usefully explains that omitting 'start' appends the clip after current track content, but it does not cover permissions, draft prerequisites, overwrite behavior, or error conditions for this mutation tool.

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

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

The description is two focused sentences with no wasted text. The core action is front-loaded, followed by the most important behavioral detail.

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 eight fully documented parameters and no output schema, the description is largely complete: it states the action and the key default for 'start'. It could better mention draft prerequisites or mutation side effects, but the rich schema covers most calling details.

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

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

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds the useful default behavior for omitted 'start', but it does not add meaning beyond the schema for the other parameters.

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: add a video or image clip to a video track. It clearly distinguishes this from sibling tools like jianying_add_audio and jianying_add_text.

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

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

The description gives clear context for when to use it by specifying video tracks and visual media. It does not explicitly name alternatives or when-not-to-use cases, so it falls short of full 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?

With no annotations, the description carries the behavioral burden and does disclose the key destructive trait: "Unsaved changes are lost." It also states the memory-release effect and the required save-first safeguard, though it does not cover permissions, error cases, or idempotency.

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

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

The description is front-loaded with the core action and effect, followed by a concise danger warning and usage condition. Every sentence contributes useful information without 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?

For a simple one-parameter close operation with no output schema, the description covers the essential action, destructive consequence, prerequisite, and intended usage scenario. Nothing critical is missing for correct invocation.

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

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

Schema description coverage is 100%, so the single "name" parameter is already documented as "Open draft name." The description only alludes to an "open draft" and adds no format or naming details beyond the schema, so baseline 3 is appropriate.

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

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

The description uses a specific verb and resource: "Close an open draft," and adds the side effect "release its memory." This clearly distinguishes it from sibling tools such as jianying_open_draft, jianying_create_draft, and jianying_save_draft.

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 explicit usage conditions: "when a draft is finished or was created by mistake," and a clear prerequisite: "call jianying_save_draft first." It lacks a direct when-not or alternative-tool comparison, but the context is clear.

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

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

With no annotations, the description carries the full burden. It usefully discloses the non-obvious default that omitting width/height makes the canvas adopt the first video's resolution, and mentions returning the draft structure. It says nothing about where the draft is written, whether a subsequent jianying_save_draft is required for persistence, or what permission/filesystem preconditions 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?

Three short sentences, front-loaded with what the tool does, followed by the one genuinely non-obvious parameter rule. No filler, though the aspect-ratio advice reads slightly like a tip rather than definitional 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?

No output schema exists, and "return its structure" is vague about what a draft structure actually contains. For a disk-writing mutation with no annotations, the missing lifecycle context (persistence/save requirement, drafts root default, run-twice behavior on duplicate names) leaves 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 coverage is 100%, so baseline is 3; the description earns above that by explaining the coupled semantics of width/height and their fallback behavior, which the schema does not convey. fps, overwrite, and draftsRoot are left entirely to 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?

"Create a new JianYing draft and return its structure" names a specific verb and resource, and the create-vs-open distinction against jianying_open_draft is implicit in the verb. It stops short of explicitly differentiating itself from the other lifecycle siblings (open/save/list), so not 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?

It gives concrete guidance for choosing width/height (1080x1920 for 9:16, 1920x1080 for 16:9) and states the omission behavior, which is genuine usage help. But there is no guidance on when to call this versus jianying_open_draft or jianying_list_drafts, and no prerequisites stated.

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 burden. It discloses the open-draft prerequisite and that a file is written, but omits important operational details: overwrite behavior, whether existing files are refused or replaced, any permission requirements, and whether the export is read-only with respect to the draft. This is a significant gap for a tool that writes to disk.

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 tightly written sentence with the action and output format front-loaded and no wasted words. It efficiently conveys the essential operation and purpose.

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

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

Given a simple file-export operation, 100% schema coverage, and no output schema, the description covers the basic purpose and prerequisite. But without annotations it should say more about overwrite behavior and side effects; the description alone leaves an agent guessing about file collision handling.

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

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

Schema description coverage is 100%, so the schema already documents name, overwrite, and outputPath thoroughly. The description adds no parameter-level meaning beyond what the schema provides, which is acceptable but not value-adding; 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?

States a specific verb ("Export"), a specific resource ("text track of the open draft"), and a concrete output format ("SRT subtitle file"). It is clearly distinct from siblings like save_draft or add_subtitles, but it does not explicitly name alternatives or contrast against them.

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

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

Provides an implied use case — checking captions in any subtitle editor — which suggests this is for external review rather than editing the draft. However, it does not state when to prefer this over save_draft or inspect_draft, nor does it mention prerequisites beyond the draft being open.

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; it implies a non-mutating inspection and lists the returned structure, which is real value. It does not state failure behavior (e.g. what happens if no draft is open) or whether the read has any side effects, so gaps remain.

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

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

Two sentences, zero waste, and the core action plus return payload is front-loaded before the usage hint. Nothing redundant with the name or schema.

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

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

With no output schema, the description correctly compensates by enumerating the returned timeline fields. For a single-parameter read tool this is nearly sufficient, though it omits the precondition that a draft must already be open via jianying_open_draft.

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% for the single 'name' parameter, so the schema already documents it; baseline 3 applies. The phrase 'the open draft' loosely confirms the parameter means the currently open draft, but adds no new syntax or constraint information.

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 ('Return the structured timeline of the open draft') and enumerates the payload (tracks, segments, timing, materials). Scoping to 'the open draft' separates it from jianying_list_drafts (all drafts) and from the mutating add_*/remove_*/save_* 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?

'Use this as the acceptance check after editing' gives a concrete trigger tied to the sibling mutation tools, so the agent knows when to reach for it. It stops short of naming an alternative or an explicit when-not condition, but the usage context is unambiguous.

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, but it does disclose the return payload (duration, canvas size) — useful since there is no output schema. It says nothing about recursion depth, missing/invalid drafts root handling, or performance, which matters for a filesystem-scanning 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?

Two tight sentences, zero filler, with the resource scope and returned fields front-loaded and the usage cue second. Nothing could be removed without losing 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 one-optional-parameter, read-only listing tool with no output schema, the description covers what it lists and what it returns, which is most of what an agent needs. Only edge-case behavior for the drafts root override is left 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 100% and the single optional draftsRoot parameter is already documented in the schema, so the baseline of 3 applies. The description alludes to the "drafts root" but adds no default-value or override semantics beyond the schema.

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

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

States a specific verb (List) plus resource (JianYing drafts under the drafts root) and even names the returned fields (duration, canvas size). It is distinguishable from open/create/add tools, though it doesn't clarify how it differs from the nearby jianying_inspect_draft 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?

"Use this before opening an unknown draft" gives a clear, actionable usage context and implies the alternative (jianying_open_draft) should follow it. It doesn't state exclusions or mention jianying_inspect_draft, so a sibling could still be ambiguous.

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 the highest-risk behavior: overwrite deliberately discards the existing draft. It also states the return value (timeline structure). It omits the session/lifecycle implication of the open/close pair (does the draft stay locked until jianying_close_draft?) and error behavior for a missing name.

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

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

Three short sentences, no filler, and the core action is front-loaded before the routing hint and the destructive-flag caveat. 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?

Absent an output schema, the description usefully names what comes back (timeline structure), and it covers the one dangerous option. What's missing is the open/close session relationship implied by jianying_close_draft, which an agent needs to use this tool correctly in a workflow.

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% and all three parameters carry their own explanations, so the schema does the heavy lifting. The description reinforces overwrite's risk but adds no syntax or format detail for name or draftsRoot beyond what is already structured. 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?

States a specific verb and resource ("Open an existing JianYing draft by name") plus the effect ("return its timeline structure") and the intent ("so work can be resumed"). An agent can distinguish this from jianying_create_draft and jianying_list_drafts 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?

Explicitly routes from a listing step ("a draft listed by jianying_list_drafts") and gives a clear conditional rule for the overwrite flag versus resuming. However, it says the tool is used "to inspect" a draft, which overlaps with the sibling jianying_inspect_draft and never resolves when to pick one over the other.

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 burden. 'Probe' implies a read-only inspection, and the description lists the returned attributes, but it does not explicitly state safety, side effects, permissions, or failure 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?

Two short sentences, front-loaded with the action and immediately followed by the practical usage context. 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 simple one-parameter probe with a fully documented schema, the description covers purpose, usage context, and returned fields. It is nearly complete, though it could add a brief note that probing does not modify the media file.

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%, and the only parameter is clearly documented as an absolute media file path. The description adds no additional parameter meaning beyond what the schema already provides.

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

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

The description states a specific verb (probe), resource (media file), and the returned attributes (duration, resolution, type). It is clearly distinct from sibling add/remove tools, though it does not explicitly name a sibling for contrast.

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

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

It gives a clear usage condition: use before adding clips so durations can be planned. It does not describe when not to use it or name alternative probing tools, but the sequencing guidance is direct and useful.

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. It usefully clarifies the blast radius ('every clip that references the given media file') and that the operation is scoped to the timeline, but it omits whether the media file itself is untouched on disk, whether the removal is reversible/undoable, what happens when no clip matches, and whether an open-draft session is required.

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; the scoping clause ('every clip that references the given media file') is exactly the information an agent needs and nothing is wasted.

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 2-parameter mutation with no annotations and no output schema, the description covers the core action but leaves out side effects (source file preservation), the no-match/no-op case, and the error/auth behavior that an agent would need to call it reliably.

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% (both 'name' and 'filePath' are documented), so the schema already does the parameter explaining. The description adds only the linkage that filePath is matched against clips referencing it, which is marginal — the baseline 3 for full schema coverage is appropriate.

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

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

The description gives a specific verb (remove) and a precisely scoped resource (every clip referencing the given media file, from the timeline), which is clearly distinct from the additive siblings like jianying_add_video. It does not name or contrast with any sibling explicitly, which keeps it at 4 rather than 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 statement of prerequisites (e.g., that a draft must be open — only hinted at by the schema's 'Open draft name'), and no mention of alternatives such as removing individual clips or re-editing. The agent must infer the context of use entirely.

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

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

No annotations are provided, so the description carries the full burden. It does disclose a useful behavioral trait – the draft only becomes visible to JianYing after saving – but omits overwrite/idempotency behavior, failure modes, and whether existing drafts are clobbered.

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

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

Two sentences, front-loaded with the action and followed by the critical ordering constraint. No filler, 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?

For a one-parameter terminal save operation with no output schema and no annotations, the description covers purpose and workflow position adequately. Minor gaps remain around failure behavior and whether a prior draft is overwritten.

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% ('Open draft name'), so the schema already documents the single parameter. The description adds no format, uniqueness, or naming-constraint detail beyond what the schema provides, making 3 the appropriate baseline.

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

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

States a specific verb and resource: 'Write the current timeline to disk as a JianYing draft.' An agent can distinguish this finalization step from siblings like jianying_create_draft or jianying_open_draft. However, it never explicitly contrasts itself with those siblings by 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?

Gives an explicit sequencing rule: 'Call this last,' which tells the agent when this tool belongs in the workflow. 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.