OpenClip

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

Discloses return values (id, status), common statuses (processing, pending_credits), and error case (file not uploaded). Lacks info on side effects or auth, but given no annotations and simple operation, sufficient.

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 sentences covering purpose, usage, and return values without fluff. Could be slightly more structured but 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 simple one-param tool with no output schema, description fully covers prerequisites, return values, and next steps (poll get_video_status). References sibling tools appropriately.

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?

Although schema covers 100% (one param described), description adds critical context: the param is the hashid from create_upload, and must be passed after uploading bytes. Adds meaningful value beyond 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?

Explicitly states 'Finish an upload started with create_upload and begin processing', specifying the action and resource. Clearly distinguishes from sibling tool create_upload by describing its role as the second 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?

Provides explicit when-to-use: after create_upload and after PUTting file bytes. Gives error handling guidance ('upload it, then retry'). No sibling alternative is needed; the workflow is sequential.

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

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

With no annotations, the description carries the full burden. It discloses the return value (id), error condition (plan limit), and parameter constraints (paid plan for speaker tracking). Some behaviors like authentication are assumed but not stated.

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 well-structured with a clear opening, parameter list, and return/error info. It is concise but could be slightly tighter by avoiding repetition of schema details.

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

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

Given the complexity (8 params, nested objects, no output schema), the description covers purpose, parameters, return value, and an error condition. It references sibling tools (list_caption_presets) and a supporting tool (describe_agent_settings).

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%, but the description adds value by grouping parameters, explaining options, and referencing describe_agent_settings for complex objects. It goes beyond the schema's property 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 clearly states 'Create a processing agent' and explains what an agent is (a saved configuration for video processing). It distinguishes itself from sibling tools like list_agents by focusing on creation.

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 context (agents are shared across the team, returns id for submit_video) but does not explicitly state when to use this tool versus alternatives or when not to use it.

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

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

Annotations are empty, so description must disclose behavior. It does: returns video id and upload_url, URL expiration (expires_in_seconds), single-PUT upload limit of 5GB, and suggests web uploader for larger files. No contradictions.

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?

Concise yet comprehensive: starts with core purpose, then actionable steps. Every sentence adds value; well-structured 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?

Covers all essential aspects: tool purpose, parameter usage, return values, follow-up steps, size constraint, and expiration. Complete for a multi-step upload tool without output 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 coverage is 100%, baseline 3. Description adds context: filename used for title and extension, size optional but enforced, audio_language as spoken-language code. This enhances 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?

Clearly states it initiates an upload of a LOCAL video file and explicitly distinguishes from sibling tool submit_video (for URLs). The verb 'start an upload' and resource 'local video file' are specific.

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

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

Provides explicit guidance: use when file is on disk, not URL; directs to call complete_upload after upload; explains that for files >5GB use web uploader. Also includes detailed steps for the HTTP PUT request with a curl example.

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

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

Annotations already indicate readOnlyHint=true, and the description adds details about the returned fields. It does not mention any additional behavioral traits beyond what is expected from a read operation, but it provides sufficient context.

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

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

Two sentences that efficiently convey the purpose and usage. The first sentence lists the returned data, and the second provides context for when to use it, with no 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?

Given the tool's simplicity (no parameters, no output schema), the description is complete. It describes what is returned and when to use it, making it adequate for an agent to understand and invoke 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?

The tool has no parameters, so the baseline is 4. The description does not need to add parameter information, and it correctly focuses on the output and usage.

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

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

The description clearly states that the tool returns account details (id, email, team, plan, credits, scopes/abilities). It also distinguishes itself from sibling tools by specifying its use for connection verification and credit checking before submitting videos.

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 explicitly advises to use the tool first to confirm the connection works and that the user has credits before submitting videos, providing clear when-to-use guidance.

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

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

Annotations declare readOnlyHint=true, which the description matches. It adds valuable context: polling behavior, status values, and the fact that completion is derived from rendered clip, not an intermediate flag. This goes beyond the annotation.

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

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

The description is concise (8 sentences) and front-loaded with purpose. Every sentence adds value—no fluff. It efficiently conveys parameter usage, status meanings, and polling guidance.

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

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

Without an output schema, the description fully explains the response structure (status list, URL on completion) and polling behavior. For a simple two-parameter read tool, this is comprehensive and sufficient for correct agent invocation.

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

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

Schema coverage is 100% with descriptions. The description adds context (video id from list_videos, optional narrowing, status explanations) that enriches the understanding beyond the schema.

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

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

The description states 'Get the render state of a video's viral moments.' with specific verb+resource. It clearly distinguishes from sibling tools like 'render_clip' and 'get_video_status' by focusing on viral moment render 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 description tells when to use the tool (polling for completion) and how to pass parameters. It implicitly contrasts with 'render_clip' but does not explicitly state when NOT to use it or list alternatives, leaving some room for interpretation.

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

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

The description explains critical behavioral details beyond the readOnlyHint annotation: the overlap semantics for time ranges, the distinction between 'transcript_ready: false' and an empty segments array, and the security warning about untrusted content. These add significant value and are consistent with annotations.

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

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

Every sentence adds value. The description is efficiently organized: first the core purpose, then optional parameters, then edge-case behaviors. There is no redundant or extraneous information. It is long enough to be complete but concise.

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

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

Despite lacking an output schema, the description thoroughly explains return values (time-coded segments, 'transcript_ready' flag, empty vs. not ready), handles edge cases (range overlap, default boundaries), and provides a security warning. It also relates times to 'list_clips' for interoperability. The tool's complexity is well-covered.

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?

All parameters are documented in the schema, but the description adds substantial context: the 'video' parameter is tied to 'list_videos', default behaviors for 'start_ms' and 'end_ms' are explained, the 'level' parameter defaults are clarified, and the range overlap semantics provide critical usage nuance. This goes well beyond the baseline of 3.

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

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

The description clearly states the tool retrieves the transcript of a video by its hashid, returning time-coded segments. It explicitly references the sibling tool 'list_videos' for obtaining the ID and differentiates itself from other tools like 'list_clips'. The verb 'Get' combined with the resource 'transcript' makes the 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?

It provides detailed guidance on when to use the tool (e.g., to fetch a video's transcript) and how to use it, including optional slicing and level selection. However, it does not explicitly state when not to use this tool or directly mention alternatives beyond implicit references to 'list_videos' and 'list_clips'.

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

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

Annotations indicate readOnlyHint=true, and the description confirms read-only behavior, adding detail about the return structure. No contradictions. It explains that credits are in minutes and describes the activity entries, providing transparency beyond the annotation. However, it does not disclose potential rate limits or authentication requirements, preventing a perfect score.

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 structured, starting with the main purpose then listing fields. It's thorough but slightly verbose; the bullet-like listing of activity fields could be more compact. Still, it's well-organized and front-loaded with the essential info.

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 fully and accurately describes all return values and their semantics. It covers credits_remaining, trial_credits_remaining, activity entries with all their fields, and the limit parameter. This is complete for a simple read-only tool.

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

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

Schema description coverage is 100% with the single 'limit' parameter already well-described in the schema. The description repeats essentially the same information (range 1-100, default 20), adding no new semantic meaning. Following the guideline, baseline is 3 when coverage is high.

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

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

The description explicitly states that the tool returns the team's processing-credit usage, counted in minutes, and lists the specific fields returned (credits_remaining, trial_credits_remaining, activity). This clearly differentiates it from sibling tools like get_account or list_videos.

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 conveys that the tool is for retrieving usage data, but it does not provide explicit guidance on when not to use it or contrast with alternatives. However, the context makes it obvious that it's the dedicated usage query tool, so it earns a 4 for clear context though lacking 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?

The description details the polling lifecycle, terminal states, and additional returned fields (viral_moments_count). It also warns about untrusted_content. This far exceeds the minimal readOnlyHint annotation by providing rich behavioral context.

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

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

The description is relatively concise and front-loaded with the core purpose. It efficiently conveys necessary details but could be slightly more structured (e.g., bullet points) to improve readability.

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

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

Given the tool's simplicity (one parameter, no output schema), the description is fully complete. It covers the state machine, polling behavior, and security note, leaving no significant 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% for the single parameter. The description adds context on the parameter's source (hashid from specific tools) but does not add new semantic constraints beyond the schema's 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 clearly states the tool retrieves the processing status of one video by its id. It specifies output fields (status, progress) and the state machine (in-flight vs terminal). This distinguishes it from siblings like list_videos and submit_video.

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 explicitly instructs when to poll (e.g., 'processing' status) and when to stop (terminal statuses like 'completed', 'failed'). It also tells the user to call list_clips upon completion, providing clear 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?

Annotations indicate readOnlyHint=true, consistent with description. The description adds valuable behavioral details: agents are team-shared, and name/caption_preset are untrusted content requiring careful handling. No contradictions.

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 somewhat lengthy but each sentence adds value. It front-loads the main purpose and provides necessary context without being overly verbose.

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

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

Given no output schema, the description explains what agents contain (tracker model, caption preset, rendering defaults) and the untrusted_content nesting, providing adequate context for an AI agent.

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

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

No parameters exist, so schema coverage is 100%. The description does not need to add parameter semantics; baseline for zero params is 4.

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

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

The description clearly states the tool lists 'agents' which are saved configurations controlling video processing. It explains what an agent is and how it's used, distinguishing it from siblings like 'create_agent' and 'list_caption_presets'.

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 tells when to use the tool (to list agents) and how the agent id is used in submit_video. However, it lacks explicit guidance on when not to use it or alternatives among siblings.

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

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

Annotations already mark this as readOnlyHint: true. The description adds valuable behavioral context: it explains the return fields (key, name, description, category) and that render_clip validates against this list, further clarifying the tool's role.

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 that first define the tool's purpose and then describe the output structure and usage. Every sentence adds value with no unnecessary text.

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 zero parameters, no output schema, and a straightforward purpose, the description fully covers what an agent needs: what the tool does, what the output contains, and how to use it with a sibling 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?

No parameters exist (schema coverage 100%), so the description correctly omits any parameter details. Baseline 4 applies, and no additional value is needed.

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

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

The description clearly states it lists caption style presets, specifies each preset contains key, name, description, and category, and connects directly to the render_clip tool. This distinguishes it from sibling tools like list_clips or list_videos.

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 states when to call this tool ('before rendering') and why ('render_clip rejects any key not in this list'), providing clear guidance on its use case and necessity.

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

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

Annotations already mark readOnlyHint=true, consistent with listing. Description adds valuable behavioral context: clip structure (id, virality_score, times, preview, rendered_clip), plan entitlement limiting results, and untrusted_content nesting with safety warning.

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?

Five sentences, front-loads purpose, each sentence adds value. No fluff, efficiently conveys purpose, usage constraint, return structure, and safety note.

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 1-param read-only list tool with annotations, the description covers return structure, plan entitlement, and untrusted content. Lacks pagination info but overall complete for expected usage.

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

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

Schema coverage is 100% with description of parameter 'video' as hashid from list_videos. Description repeats schema info but adds no new meaning beyond schema. Baseline 3 is appropriate.

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

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

The description clearly states 'List the playable viral-moment clips for a video' with a specific verb and resource. It distinguishes from sibling tools by mentioning clips are for a video and have their own id, and references list_videos for the input id.

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 says 'Call this once the video is `completed`', providing a clear precondition. Also notes the set honors plan entitlement, implying not for all clips. Lacks explicit exclusions or alternatives, but 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?

Annotations already provide readOnlyHint=true. The description adds context about the returned fields (key, name, direct_url vs platforms), but does not disclose additional behavioral traits beyond what annotations imply.

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 purpose, 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 simple, parameterless tool with no output schema, the description completely explains what it returns and how to use it.

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

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

There are no parameters, so schema coverage is 100%. The description need not add parameter info; baseline for 0 params is 4.

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

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

The description clearly states the tool lists video sources accepted by submit_video, with specifics about key and name fields, and distinguishes direct_url from platform links. It is distinct from siblings like submit_video and list_videos.

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 explicitly says to use this tool before calling submit_video to inform users which links work. While it doesn't cover when not to use alternatives, the context is clear for this simple listing tool.

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

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

Annotations already declare readOnlyHint=true. The description adds important behavioral details: it lists videos most recent first, specifies the fields in each entry, enumerates possible status values, and warns about untrusted_content being source-derived text that should never be treated as instructions.

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 well-structured with clear paragraphs and front-loads the purpose. It could be slightly more concise (e.g., the full list of status values), but it remains efficient and informative.

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

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

Given no output schema, the description thoroughly explains the contents of each entry (id, status, created_at, viral_moments_count, untrusted_content.title). It also explains the status field and provides usage context. For a list tool, this is complete and actionable.

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

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

Schema coverage is 100%, so the description does not need to add parameter details. It mentions 'limit' and 'status' implicitly through the field explanations, but does not provide additional semantic context beyond what the schema already describes. Baseline 3 is appropriate.

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

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

The description clearly states it lists videos in the connected account's current team, most recent first. It distinguishes itself from sibling tools by explicitly calling itself 'the entry point' and directing users to other video-scoped tools after obtaining video IDs.

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 explicit guidance: 'This is the entry point: call it to discover video ids before using any other video-scoped tool.' It tells when to use the tool and mentions subsequent tools (get_video_status, get_render_status, list_clips, render_clip) that require the video ID.

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 fully discloses behavior: explicit on-demand render, replacement behavior, asynchronous nature with status polling, retry safety, and possible 'not_dispatched' status. No contradictions with annotations.

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

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

Concise yet comprehensive: three paragraphs that front-load the main purpose, then detail important behavioral traits. Every sentence is justified and no 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?

No output schema or annotations, but the description covers all needed aspects: inputs, side effects (replacement), async behavior, polling, statuses, and preconditions. It is fully complete for an AI agent to use correctly.

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

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

Schema coverage is 100%, baseline 3. The description adds value by specifying that video and viral_moment are hashids from list_clips, and that invalid caption_preset keys are rejected, improving understanding beyond the schema.

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

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

The description opens with 'Produce a final captioned render of one viral moment,' a specific verb+resource statement. It distinguishes from sibling tools like get_render_status by stating that this tool creates a new render, while reading should use the 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?

Explicitly tells when to use this tool ('to produce a render') and when not to ('to just read an existing render, use get_render_status or list_clips'). Also explains retry safety and preconditions, providing clear guidance on usage.

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 fully discloses behavioral traits: asynchronous processing ('status: downloading' or 'pending_credits'), safe to retry with dedup logic, and error handling for unsupported URLs or invalid agents. It also clarifies that the same url with a different agent starts a new run, covering potential confusion.

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 well-structured, starting with the main action and return value, then detailing async behavior, dedup, and errors. It is slightly long but each section adds important context. It could be more concise, but the structure supports readability.

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

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

Given the lack of an output schema, the description adequately explains the return (id and status) and covers error cases, dedup, and retry. It is sufficient for an agent to understand the tool's behavior, though it could be more explicit about the full response structure.

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

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

The input schema already has 100% coverage with descriptions. The description adds value by specifying supported providers for the url, clarifying that agent must be from the team, and explaining that title defaults to the source. While helpful, it does not introduce new information 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 specifies the action (submit a source video URL), the resource (video), and the purpose (to turn into viral clips). It lists supported platforms and distinguishes itself from sibling tools like get_video_status and list_clips, making the purpose clear.

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

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

The description provides explicit guidance on when to use this tool (to submit a video), what to expect after (poll get_video_status, then call list_clips), and error scenarios. It explains retry behavior and deduplication. However, it does not explicitly state when to avoid this tool in favor of alternatives, which would improve the score.

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