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

No annotations are provided, so the description must convey behavioral traits. It details the return dict (task_id, video_id, status, progress, video_url, seconds, size, error), which is transparent about output. However, it does not mention that this is a read-only operation, whether it can be called multiple times, or if there are side effects. The description covers the output but lacks operational 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 structured as a docstring with clear sections: purpose, args, and returns. It is concise with no unnecessary words, and the most important information (purpose and parameter origins) is front-loaded.

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 with two parameters and an output schema (detailed in the description's returns section), the description is complete. It covers purpose, parameter sources, and return fields, providing sufficient information for an agent to invoke the tool correctly.

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

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

Schema description coverage is 0%, so the description must add meaning. It explains that both video_id and task_id are returned from text_to_video, and are alternative identifiers. This adds critical context beyond the bare schema, enabling correct 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 the tool's purpose: 'Check the status of a video generation task.' This is a specific verb-resource pair, and it distinguishes from sibling tools like text_to_video (which initiates generation) and text_to_image (different modality).

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 ties the parameters to the output of text_to_video, indicating the context of use: after initiating a video generation task. It also notes that the two parameters are alternatives. However, it does not explicitly state when not to use it or provide alternative tools for other scenarios.

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 bears full responsibility. It discloses that the tool generates images, accepts image URLs, and returns a dict with url, local_path, etc. It mentions saving locally and return modes. It does not cover potential rate limits or file size constraints, but the core behavior is 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?

The description is well-structured with 'Args' and 'Returns' sections, making it easy to parse. It is concise, with only minor redundancy in the opening sentences. Every sentence provides value, though a slight trim could improve focus.

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 7 parameters (2 required) and an output schema, the description covers all inputs and outputs. It explains each parameter's role and the return format. No critical gaps are present, though it could mention that 'images' must be URLs. Overall, it is complete enough for an agent to use effectively.

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

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

Schema description coverage is 0%, meaning no parameter descriptions in the schema. However, the tool description lists all 7 parameters with explanations, defaults, and allowed values (e.g., model names, size formats). This adds significant meaning beyond the bare schema, fulfilling the compensation requirement.

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 new image(s) based on reference image(s) and a text prompt.' It uses specific verbs ('generate') and resources ('image(s)'), and distinguishes from sibling tools like text_to_image, which lacks reference images. The title is absent but the description compensates.

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 explains that reference images are required and a text prompt guides generation. It lists parameters and their defaults, providing context. However, it does not explicitly state when to use this tool over alternatives (e.g., text_to_image) or when not to use it. Still, the purpose is clear enough for an agent to infer appropriate 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?

The description discloses the async nature (polls until completion, may take minutes) and return values (dict with video_id, etc.), which are beyond the schema. With no annotations, this is valuable context, though it lacks details on failure modes or quotas.

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 and well-structured: a one-sentence summary, one paragraph on async behavior, then a bulleted Args list. Every sentence adds value, and the most important information is front-loaded.

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 complex async tool with many parameters, the description covers input, process, and output comprehensibly. It explains the polling mechanism and return dict, making the tool's behavior fully understandable.

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 11 parameters are explained in the Args list, adding meaning beyond the bare-bones schema (0% coverage). For example, num_frames includes the '8n+1 rule' and common values with approximate durations, which is highly informative.

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 animates a static image into a video, specifying input types (image URL/base64, text prompt). It is specific and distinct from siblings like text_to_video (no image input) or image_to_image (no video output), but does not explicitly differentiate usage cases.

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 through required inputs (image and prompt), suggesting when the tool is appropriate. However, no explicit guidance on when to use alternatives or when not to use this tool is provided, leaving the agent to infer 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?

With no annotations provided, the description fully covers behavioral traits: async operation with polling, potential multi-minute runtime, return dict with video_id/status/url/path/seconds/size. It also explains the 8n+1 frame count rule, which is critical for correct usage.

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, followed by structured Args section using consistent formatting. Every sentence adds value without redundancy, given the complexity of the tool.

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 an 11-parameter tool with 2 required, no enums, and existing output schema, the description comprehensively covers all aspects: input requirements, parameter defaults and ranges, async behavior, return structure, and output location. No gaps are evident.

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

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

Schema coverage is 0%, yet the description adds rich semantics for all 11 parameters: explains the 'images' list requirement, default model, common num_frames values with duration approximations, frame_rate range, optional negative_prompt/seed/steps, and output_dir default. This far exceeds minimal schema 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?

The description clearly states it generates a smooth video transitioning between multiple keyframe images, with text prompt guidance. It uniquely distinguishes from sibling tools like image_to_video (single image) and text_to_video (no images) by requiring 2+ image URLs as keyframes.

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 specifies to provide 2+ image URLs and that it's an async operation polling for completion. It hints at when to use (multiple images) but does not explicitly forbid single-image use or mention alternatives like image_to_video for single-image input.

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. It discloses the tool's behavior: generating images, saving to disk, and returning a dict. However, it does not mention authentication requirements, rate limits, or potential side effects beyond file saving.

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: a one-line purpose, bullet points for model options, an Args section with parameter details, and a Returns section. It is front-loaded with the core action and remains concise without unnecessary 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?

The description covers all parameters, model choices, and return format. It lacks error handling information and prerequisites (e.g., API key setup) but is otherwise sufficient for an agent to invoke the tool correctly. The presence of an output schema makes the return description less critical.

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 has 0% description coverage, so the description fully compensates. Each parameter (prompt, model, size, n, images, output_dir, return_mode) is clearly explained with constraints, defaults, and allowed values (e.g., n=1-4). This adds significant value beyond the raw 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 clearly states the tool generates images from text using Agnes AI. The verb 'generate' and resource 'images from text' are specific. Sibling tools like image_to_image and text_to_video are differentiated by name and context, making 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?

The description provides guidance on model selection, recommending agnes-image-2.1-flash for enhanced quality. However, it does not explicitly state when to use this tool over siblings like image_to_image or text_to_video, although the tool name suffices for basic differentiation.

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?

In the absence of annotations, the description discloses the async polling behavior and the return format (dict with keys). It does not mention potential side effects, but writes are not expected. It could add more on error handling or timeouts.

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 sections for Args and Returns, but it is somewhat lengthy. Every sentence adds value, though some parameter details could be tighter. Still, it is appropriately front-loaded.

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 complexity (13 parameters, async behavior, output schema), the description covers purpose, parameters, behavior, and return format adequately. It is complete enough for an agent to select and invoke the tool correctly.

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

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

Schema description coverage is 0%, so the description bears full responsibility. It explains all 13 parameters with defaults, constraints (e.g., num_frames formula), precedence (image vs images), and common values, adding substantial 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?

The description clearly states 'Generate a video from text (and optional image(s))', which is a specific verb-resource pair. It also distinguishes from siblings like image_to_video and text_to_image by indicating the primary input modality.

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 notes that the operation is async and polls until completion, giving temporal expectations. It does not explicitly state when not to use this tool or name alternatives, but the context of siblings and the parameter descriptions imply usage scenarios.

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