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 the key behavior ('adding more motion and content after the original video ends') and mentions the return of a Task ID, implying an asynchronous task. However, it does not mention potential side effects, requirements, or whether the original video is modified, which would be valuable for a generation 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 well-structured with a clear intro, a bulleted 'Use this when' list, and a brief 'Returns' section. It is slightly verbose but every sentence earns its place by clarifying purpose and usage. No filler 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?

For a 4-parameter tool with output schema, the description is fairly complete: it covers purpose, usage scenarios, and return values. It lacks explicit mention of asynchronous behavior or a comparison with luma_extend_video_from_url, but the 'Task ID' and 'previous generation' hints mitigate this. Given the moderate complexity, it is adequate.

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?

Input schema has 100% description coverage, so the baseline is 3. The description adds no extra parameter details beyond what the schema already defines for prompt, video_id, callback_url, and end_image_url. It does not repeat or expand on schema descriptions, so no additional value.

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 function with a specific verb and resource: 'Extend an existing video with additional content.' It distinguishes from siblings by specifying 'previously generated video' and 'after the original video ends,' which aligns with the tool name and separates it from luma_extend_video_from_url.

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 'Use this when' guidance with three concrete scenarios: video too short, continue story/motion, build longer piece by piece. It does not mention when to use alternatives like luma_extend_video_from_url, but the context of 'previously generated video' implies this is for existing Luma generations.

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 present, so the description carries the burden. It hints at async behavior by mentioning a returned Task ID and notes the URL must be from a previous generation, but it does not disclose details about polling, error handling, or potential side effects.

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

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

The description is well-structured and concise, starting with a clear statement, followed by a comparative note, usage bullets, and a return note. Every sentence adds value without redundancy.

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

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

With an output schema present and a clear comparison to a sibling, the description covers the core purpose, usage conditions, and return type. It lacks deeper async workflow details, but is sufficient for tool selection and 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 descriptions cover 100% of parameters, so the baseline is 3. The description adds no additional parameter semantics beyond what the schema already provides, such as the meaning of prompt or callback_url.

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 'Extend an existing video using its URL' with a clear verb and resource, and distinctly separates itself from the sibling luma_extend_video by noting URL instead of video 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 compares to luma_extend_video and lists specific 'Use this when' bullets, giving the agent clear criteria for selecting this tool over alternatives.

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 provided, so description carries full burden. It mentions return values, but does not disclose async nature, generation time, or any side effects. The timeout parameter hints at long duration, but description implies immediate return. Could be more transparent.

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: single line for purpose, explanatory paragraph, bullet list for usage, explicit alternative, and return format. 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?

With output schema available, description adequately covers return values. All 6 parameters have schema descriptions. Sibling tools are referenced. Lacks only async workflow details, but still fully functional.

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 each parameter is already described. The description adds only minor context (like prompt examples) but nothing significant beyond the 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?

Clearly states 'Generate AI video from a text prompt' with specific verb and resource. Explicitly distinguishes from sibling tool luma_generate_video_from_image by stating when to use each.

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 'Use this when:' bullet list and directly tells when not to use it (have reference images), naming the alternative tool. Complete 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?

No annotations exist, so the description must disclose behavioral traits. It mentions generating 'smooth motion' and returns 'Task ID and generated video information.' However, it does not clarify if the operation is asynchronous (suggested by callback_url parameter), potential rate limits, or other side effects. For a generation tool, more transparency about the async nature would be beneficial.

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 about 100 words, well-structured with bullet points for use cases. It is concise and front-loaded with the main action. However, it could be slightly more concise by avoiding redundancy in the use case list.

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 parameters, generation tool, likely async), the description covers the core functionality but lacks details on the async workflow (returning a task ID and then later polling) and explanation of parameters like callback_url and timeout. The output schema likely covers return values, but the description should mention the async behavior for completeness.

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 adds meaning by explaining the role of start_image_url and end_image_url and the constraint on providing at least one. However, it does not elaborate on parameters like timeout, callback_url, or loop beyond what the schema already defines. It adds marginal value.

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: 'Generate AI video using reference images as start and/or end frames.' It specifies the action (generate), resource (video from images), and scope (using start/end frames). This distinguishes it from sibling tools like luma_generate_video (no images) and luma_extend_video (extend existing 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 provides explicit use cases: when you have a specific image to animate, want a transition between two images, or need control over visual content. It also states the constraint 'At least one of start_image_url or end_image_url must be provided.' While it doesn't explicitly say when not to use it, the use cases are clear and help the agent choose between this and alternatives.

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, so description covers behavioral traits. Discloses task states and return values. Does not mention rate limits or auth, but for a simple read tool this is acceptable.

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

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

Well-structured with bullet points for usage and task states. Front-loaded purpose. No wasted sentences.

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 key aspects: purpose, when to use, task states, return summary. Output schema exists, so no need for detailed return spec. Adequate for a straightforward polling 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?

Input schema has one parameter with description. Description adds value by explaining task_id source and summarzing return fields. With 100% coverage, baseline 3, and description enhances 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 it queries status and result of a video generation task. It distinguishes from sibling generation/extend tools by focusing on retrieval. Specific verb+resource with context.

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 scenarios (check completion, retrieve URLs). Describes task states. Does not explicitly state when not to use, but context implies it's for after generation, not for batch retrieval (use luma_get_tasks_batch).

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 present, but the description accurately describes the read-only query behavior and mentions status/video information returns. The parameter description adds a max batch size constraint, aiding transparency.

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

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

The description is short, front-loaded with purpose, uses clear sections, and every sentence adds value with no unnecessary 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?

Given a single parameter and existing output schema, the description sufficiently covers purpose, usage, and return value. It is complete for a simple batch query 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 coverage is 100% with a clear description of task_ids including the max batch size. The main description adds no further parameter details beyond the schema, so it meets the baseline but does not exceed.

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 'Query multiple video generation tasks at once' using a specific verb and resource, and distinguishes from the sibling luma_get_task (singular) by emphasizing batch efficiency.

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 lists when to use with bullet points and contrasts with luma_get_task by stating it is 'More efficient than calling luma_get_task multiple times', providing clear context and alternatives.

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 provided, but description adequately discloses it returns a categorized list. No side effects implied. Could mention idempotence but not 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?

Four sentences, front-loaded with purpose. No wasted words. Perfectly concise for a list operation.

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, an output schema exists, and sibling tools are action tools, description is complete. Could mention 'use before calling other luma_* tools' but adequate.

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 defined; schema coverage is 100% vacuously. Baseline 4 applies as description adds no param info but none 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?

Description clearly states 'List all available Luma API actions and corresponding tools.' Verb 'list' and resource 'actions' is specific. Distinguishes from sibling action tools like luma_generate_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?

Explicit context: 'Reference guide for what each action does and which tool to use.' Implies usage for discovery. No exclusions needed as it's a unique list operation.

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?

Without annotations, the description carries the burden. It indicates a read-only listing operation and specifies the return format as a table with descriptions and use cases. No side effects are expected, so this is 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?

The description is three sentences: it states the function, explains the benefit, and describes the return. Every sentence adds value without redundancy.

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

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

Given zero parameters and a straightforward operation, the description is fully complete. It covers purpose, usage context, and return expectations. The output schema exists but the description already summarizes the return.

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 the baseline score applies. The description adds no parameter-specific information, which is appropriate since none exist.

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 all available aspect ratios for Luma video generation, and it distinguishes from sibling tools like luma_generate_video or luma_extend_video, which are about generation and extension, not enumeration.

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 advises to use this tool to understand which aspect ratio to choose, providing clear context. While it doesn't explicitly mention when not to use it or name alternatives, the task is simple and no direct alternative exists among siblings.

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