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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that the karaoke style highlights the active word, but it does not disclose side effects (e.g., whether it overwrites the clip), reversibility, output format, or any prerequisites. For a mutation tool, this is a significant 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?

The description is two sentences with zero redundancy, front-loading the main purpose and then adding one key behavioral detail about the karaoke style. Every word earns its place, and the structure is clean and scannable.

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

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

For a tool with 9 parameters, no output schema, and no annotations, the description is too sparse. It doesn't explain the role of most parameters, doesn't mention that it appears to be job-based (given the required job_id), and doesn't clarify what happens to the clip after styling. The description leaves too much for the agent to infer.

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

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

Schema description coverage is only 33%, and the description adds little beyond that. It mentions the karaoke style behavior, but that's already captured by the highlight_color parameter description and the style enum. Other parameters like position, font_name, font_size, and uppercase are left unexplained, and the description does not compensate for the low schema coverage.

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

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

The description uses the specific verb 're-style' and the resource 'captions of one clip', making it clear the tool modifies existing captions rather than adding new ones. The parenthetical 'clips already ship with default captions' clarifies scope and distinguishes it from any caption-adding tool among the 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?

The description implies when to use the tool (when you want to change the style of existing captions) by noting that clips already have captions, but it doesn't explicitly state when not to use it or name alternative tools like recut_clip or process_video. The guidance is implicit, not explicit.

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 does so thoroughly: it reveals the returned upload_url and upload_id, requires raw-byte HTTP PUT, states expiry and size limits, and explains the tmpfiles.org fallback lifecycle including the 60-minute expiry and signed-link refresh.

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 primary use condition and workflow, then adds constraints and fallback instructions in a logical order. Every sentence carries operational value, including exact curl examples and timing details.

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

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

There is no output schema, so the description must explain return values and next steps, and it does: upload_url, upload_id, expires_in, max_mb, and the required call to process_video. It also covers failure handling, making it complete for an agent to execute the 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?

The single optional filename parameter is fully documented in the schema as 'Original file name (optional, for the extension).' The description does not add parameter-specific meaning, but the schema coverage is 100%, 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 states a specific action and resource: reserve an upload slot for a local video file. It clearly distinguishes this from processing a video by explicitly contrasting file input with a link and by naming process_video as the follow-up step.

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 opens with 'Use when the user hands you a video FILE instead of a link,' giving a direct condition for use. It also provides a fallback path for when the sandbox cannot reach the upload URL, and a final fallback to ask the user, so an agent knows exactly how to route the task.

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 convey behavioral expectations. It implies a read-only operation (status retrieval) and mentions return contents (status, logs, clips), but does not explicitly state that it has no side effects or require any special permissions.

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

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

The description is a single, concise sentence that efficiently conveys the tool's purpose and output. There is no redundancy or extraneous 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 simple status-check tool, the description is largely complete. It mentions the statuses returned, log lines, and clips, which gives a good sense of the output. It does not cover error scenarios or edge cases, but these are not critical for such a straightforward tool.

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

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

The schema only defines job_id as a string with no description (0% coverage). The description does not compensate by explaining the parameter, though the name is self-explanatory. Given the low schema coverage, the lack of any elaboration in the description reduces the score.

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

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

The description clearly states the tool's purpose: retrieving the status of a processing job, including possible statuses and additional data. It distinguishes itself from sibling tools like process_video or list_clips by focusing specifically on job status.

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 usage context is implied rather than explicit. It is clear that this tool should be used when checking job status, but it does not explicitly state when to use it over alternatives or provide any exclusions.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool requires an authenticated user and that it returns quota information. It also mentions the failure mode of process_video, which is useful context. It does not explicitly state read-only behavior, but 'get' implies it, and there are no side effects to disclose.

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 concise sentences: the first states what the tool does, the second provides actionable usage guidance. No filler or redundancy. The information is front-loaded for quick comprehension.

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 getter with no output schema, the description adequately explains what is returned (plan and remaining minutes) and when to invoke it. It also ties into the process_video failure mode, covering the main usage scenario. The tool is straightforward, so nothing critical 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?

The tool has zero parameters and an empty input schema, so the baseline is 4. The description correctly implies there is nothing to configure, and the focus is on the return value rather than inputs.

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

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

The description clearly states the tool's purpose: it retrieves the authenticated user's plan and remaining processing minutes. It uses a specific verb (get) and a specific resource (quota), distinguishing it from sibling tools like process_video or list_clips. No ambiguity.

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 instructs when to use: 'Call before large jobs', and provides the consequence of not doing so: 'process_video fails with quota_exceeded when the balance is insufficient'. This names the alternative tool and the condition, giving the agent clear decision criteria.

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

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

With no annotations, the description carries the burden and does state the output includes titles, descriptions, download URLs, and interactive rendering in MCP Apps clients. It does not mention side effects, error conditions, or read-only behavior, but the operation is inherently a listing.

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 sentences, directly states the key output fields, and includes a notable client rendering behavior without unnecessary 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?

The tool is simple and the description covers return content, but it omits job_id semantics and any error or prerequisite details. It is adequate for a basic understanding but not fully 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?

The only parameter, job_id, has no schema description and the tool description does not explain its meaning, format, or requirements. Since schema description coverage is 0%, the description fails to compensate.

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 title 'List' and description 'The clips of a completed job' clearly identify the resource and action. However, it does not distinguish this tool from sibling tools like get_job_status or recut_clip, so it misses the differentiation expected for 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?

No guidance is given about when to use list_clips versus alternatives, nor about prerequisites such as job completion. The description is not misleading but provides no usage context.

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

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

Fully discloses the tool's behavior: it returns a job_id immediately, takes minutes, and can notify via webhook on success or failure. It also transparently explains defaults for captions and hooks, plus the force_low_quality override. No annotations were provided, so the description bears the full burden and meets it.

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 thorough and logically organized, covering input, defaults, async flow, and rights. It is somewhat verbose, with several clauses that could be tightened, but every sentence contributes meaningful detail, so the length is justified given the tool's complexity.

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

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

The description provides all necessary context for a complex asynchronous tool: input variants, default behavior, output (job_id), completion mechanisms, and required rights confirmation. Without an output schema, it still covers what the caller should expect. No gaps are apparent.

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 description adds significant context beyond the schema: it explains interactions (captions stacking, hook text, target_clips as a non-guarantee, clip length constraints, source_url vs upload_id). With 100% schema coverage already, the description enriches parameter understanding rather than repeating it.

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

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

The description clearly states the action ('Start clipping a video') and identifies the resource (a video from a URL or upload). It differentiates from sibling tools by explicitly covering the asynchronous workflow and alternative input methods, making the tool's purpose 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?

Provides explicit instructions on when to call directly (pass the user's URL without fetching it) and when to use upload_id instead. It also explains the async behavior (poll or webhook) and how to handle low-resolution warnings, giving clear usage 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 provided, the description carries the full burden of behavioral disclosure. It does reveal important behavior: TikTok posts land as drafts, Instagram and YouTube publish directly, and scheduling is optional. However, it does not disclose potential side effects (e.g., irreversible actions, rate limits, error handling) or the response format, leaving gaps for a mutating operation.

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

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

The description is three sentences, front-loaded with the core action and then providing crucial details about platform behavior, requirements, and scheduling. Every sentence adds value without redundancy or fluff.

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

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

For a tool with 7 parameters and no output schema, the description is only partially complete. It covers prerequisites and scheduling but omits details on how parameters like job_id and clip_index are used, what happens after posting (return values), and potential error conditions. The description provides a good starting point but leaves an agent guessing on several operational aspects.

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

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

Schema description coverage is only 14% (only scheduled_date has a schema description). The description adds context for scheduled_date (ISO-8601) and mentions platforms implicitly, but fails to explain job_id, clip_index, title, description, timezone, or how they relate to the publishing process. Given the low schema coverage, the description should have compensated with parameter explanations but did 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?

The description clearly states the tool's purpose: posting one clip to connected social accounts. It specifies the resource (clip) and action (post), and distinguishes from siblings by focusing on publication rather than processing, listing, or quota operations. The platform-specific behavior (TikTok draft vs direct) adds clarity.

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

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

The description provides clear prerequisites (connected social profile or Upload-Post key) and mentions optional scheduling, which helps the agent decide when to use it. However, it does not explicitly state when not to use this tool or compare it to alternatives like process_video or recut_clip, though the name and purpose make the context obvious.

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

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

With no annotations, the description must disclose behavior. It does explain that times are in the ORIGINAL source video, that segments are concatenated in order, and that going outside the clip's original range requires retained source video and re-runs the reframe engine. However, it does not disclose side effects (e.g., whether the original clip is replaced or a new one created), potential errors, or any permissions or rate limits. It covers the key mechanics but leaves significant behavioral gaps.

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

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

The description is two sentences, tightly written, and front-loads the purpose before explaining key constraints. Every clause adds value: the engine reference, time units, concatenation order, and the range/reframe condition. No fluff or repetition. This is a model of concise, structured documentation.

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

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

The tool has 6 parameters, no output schema, and no annotations, so the description must carry a lot. It covers the core behavior and the critical constraint about retained source video. However, it does not explain what the tool returns after re-rendering, how to access the result, or what happens to the original clip. An agent would not know whether the operation is destructive or returns a new clip object. Given the complexity and missing output schema, this is a significant gap.

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

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

Schema coverage is 83% (5 of 6 params described). The description adds meaning beyond the schema: it clarifies that segments are concatenated in the given order, that times are in the source video's seconds, and that reordering/dropping is possible. This goes beyond the simple 'Seconds in the source video' schema descriptions. For the one undocumented param (job_id), it's an ID that is self-explanatory. The description enhances understanding of segments and the reframe behavior, justifying a score above baseline.

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

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

The description opens with a specific verb and resource: 'Re-render one clip from a new list of source-video segments.' It names the exact operation and scope, and adds useful context ('the same engine behind the dashboard's clip editor'). This clearly distinguishes it from siblings like list_clips or add_subtitles, which are about different operations.

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 explicit guidance on when to use this tool versus alternatives. The description explains what it does but does not mention when it is appropriate or when to prefer a sibling (e.g., 'use process_video for initial processing, not here'). An agent must infer from the sibling names that this is for re-cutting an existing clip, but no direct comparison or exclusion is provided.

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