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 default model (agnes-image-2.1-flash) and multi-image composition, but lacks information about output format, side effects, authentication, or limitations. This is a significant gap for a tool of this complexity.

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 front-loaded, with three sentences covering purpose, model, and key parameter usage. It avoids fluff, though it could be slightly longer to accommodate 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?

Despite having an output schema, the 9-parameter tool with no annotations requires richer guidance. The description only covers image_paths and the default model, leaving major aspects like prompt requirements, mask usage, output_format, and when to use size/ratio unaddressed.

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 compensate. It only explains image_paths (URLs or local files) and mentions the default model; the remaining 8 parameters (prompt, size, ratio, mask_path, extra_body, return_base64, output_filename, response_format) are left unexplained.

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 with a specific verb+resource: 'Edit or compose images through Agnes img2img'. It distinguishes itself from sibling generation tools by focusing on editing/composing from existing images via image_paths.

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 usage for editing/composing rather than generating, but does not explicitly compare with alternatives like agnes_image_generate or mention when not to use this tool. It provides some usage context (URLs or local files) but no 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 the save behavior ('save returned image data when possible') and the supported input modes, but leaves the conditions of 'when possible' unclear and does not mention side effects, permissions, or failure modes. Some behavioral context exists, but major gaps remain.

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

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

The description is concise, consisting of two sentences that front-load the primary purpose and include only necessary details. No redundant or filler content is present.

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 7 parameters, no annotations, and an output schema. The description covers the core purpose and a couple of parameters, but does not provide enough context for advanced options (extra_body, response_format), the save behavior's conditions, or how the tool relates to siblings. The output schema exists, so return values need not be explained, but the tool remains under-described for its complexity.

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 compensate. It adds meaning for the size parameter ('exact pixel dimensions such as '1024x768'') and for image_urls ('image-to-image (via image_urls)'), but does not describe the required prompt parameter, extra_body, return_base64, output_filename, or response_format. This leaves most parameters under-explained.

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 identifies the tool's action ('Generate an image') with a specific resource ('Agnes Image 2.1 Flash') and adds a secondary behavior ('save returned image data when possible'). However, it does not explicitly distinguish this from sibling tools such as agnes_image_generate_v2 or agnes_image_edit.

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 usage contexts by stating 'Supports text-to-image and image-to-image (via image_urls)', giving some idea of when to use the tool. However, there is no explicit when-to-use/when-not-to-use guidance or mention of alternatives like agnes_image_generate_v2, so the usage guidance remains implicit.

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 carry the full burden. It discloses input capabilities (text/image-to-image) and the model's optimization focus, but it gives no information about output behavior, side effects, costs, or limitations, leaving important behavioral aspects unexplained.

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 (two sentences), front-loaded with the main purpose, and includes no filler. It packs relevant details about input modes and size formats, though slightly dense in the second sentence.

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 8-parameter tool, the description covers the core functionality and key parameters, and the presence of an output schema covers return values. However, several parameters (e.g., output handling) are not explained, and there is no mention of prerequisites or operational context, making it adequate but incomplete.

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 has 0% description coverage, but the description explains 'size' (tier values and legacy sizes) and 'ratio' (allowed ratios), and clarifies the role of 'image_urls' for image-to-image. Other parameters like 'extra_body', 'return_base64', 'output_filename', and 'response_format' remain undocumented, so the description only partially compensates.

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 an image with a specific model version ('Agnes Image 2.1 Flash') and a distinct focus on high-information-density visuals. It distinguishes from image editing and video tools by name/verb, but it does not explicitly compare against the sibling 'agnes_image_generate'.

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 clear context on supported input modes: text-to-image and image-to-image via image_urls, plus acceptable size/ratio formats. However, it offers no explicit exclusions or directions on when to prefer this over sibling tools like agnes_image_generate.

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 transparency burden. It discloses key behaviors: the tool blocks until completion, returns the final video URL, and may download the file locally. It does not mention failure handling or polling details, but the core behavioral contract is communicated.

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 and front-loaded with the core action. The first sentence states the primary purpose, and the next two add value about the combined behavior and return/download functionality. Every sentence earns its place with no 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?

The description explains the main workflow and the return/download behavior, and an output schema exists so return details are not needed. However, with 13 parameters and zero schema documentation, the description leaves significant gaps about how to configure the video task, including mode, image, resolution, aspect ratio, and negative prompt.

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 coverage is 0% and there are no parameter descriptions in the schema. The description only hints at one parameter-related behavior ('optionally downloads the video file') and mentions nothing about the other 12 parameters. It does not meaningfully compensate for the absent schema documentation.

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 a specific action ('Submit an Agnes video task and wait for completion') and identifies the resource ('Agnes video task'). It explicitly distinguishes itself from siblings by noting it 'Combines submit + wait into a single call', making the tool's unique role 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 gives clear context by stating it combines submit and wait, implying it is the all-in-one alternative to using agnes_video_submit followed by agnes_video_wait. However, it does not explicitly state when one would prefer the separate tools or provide exclusions, so it stops short of full 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 are provided, so the description carries full responsibility for behavioral disclosure. 'Fetch the current status' is minimal and does not reveal whether this is a poll, whether it errors on unknown video_ids, or any other behavioral traits. There is no mention of return format or side effects, though the output schema may cover returns.

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, clear sentence with no redundant information. It is front-loaded with the verb and resource, making it easy to scan. Every word adds value.

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-fetch tool, the description is adequate but has clear gaps. It lacks usage context, such as when to call it relative to submission, and does not explain the status values. Given the simple schema and output schema, it is minimally viable but could be improved with workflow guidance.

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 has one parameter (video_id) with no description (schema_description_coverage 0%). The description only repeats the parameter name ('by video_id') without adding extra meaning like where to obtain it (e.g., from agnes_video_submit) or any format requirements. This does not sufficiently 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 a specific verb 'Fetch' with a clear resource 'current status for an Agnes video task' and identifies the key identifier 'video_id'. This clearly distinguishes it from siblings like agnes_video_submit, agnes_video_wait, and agnes_video_generate, which have different actions.

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 provided on when to use this tool versus alternatives. It does not mention that it is a non-blocking status check compared to agnes_video_wait, nor does it explain the typical workflow (e.g., after submitting a video task). The description implies a simple status fetch but gives no context or 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?

With no annotations, the description carries the burden of behavioral disclosure. It reveals the automatic alignment of num_frames to the 8n+1 rule and support for keyframe animation via extra_body, but does not mention authentication, rate limits, or failure behavior.

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

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

The description is brief and front-loaded with the core purpose. The additional behavioral notes are useful, though the num_frames reference is extraneous and potentially confusing.

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 9 parameters with zero schema descriptions and no annotations, the description is insufficiently complete. It covers the return value and three modes, but leaves most parameters opaque and does not integrate with sibling workflow tools.

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 has no parameter descriptions, so the description must compensate. It explains the image parameter for image-to-video and extra_body for keyframe mode, but leaves many parameters like duration, frame_rate, and aspect_ratio unexplained. It also references 'num_frames' which is not a parameter in the schema, creating confusion.

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

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

The description uses a specific verb 'Submit' and resource 'Agnes video task', and clearly states the return of a video id for polling. This distinguishes it from sibling tools like agnes_video_status which likely only checks 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 implies the workflow of submitting a task and then polling status, which is clear context. However, it does not explicitly state when to use this tool versus agnes_video_generate or exclude any 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 exist, so the description alone must disclose side effects. It mentions polling and timeout behavior, but omits that the tool may download the video (download defaults to true) and what happens on success or failure. This is minimal disclosure.

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 entire description is a single clear sentence with no wasted words, front-loading the main action ('Poll') immediately.

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 five parameters and no annotation assistance, the description is too sparse. It does not explain the download behavior or configuration of timeout/polling, though an output schema exists for return values.

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 has no descriptions (0% coverage), and the description only clarifies that video_id identifies the task. The meanings of download, output_filename, timeout_seconds, and poll_interval_seconds are left to name inference, which is insufficient compensation.

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 'poll' with resource 'video task' and terminal conditions (completes/fails/times out). It clearly distinguishes this from sibling tools like video_submit (submitting) and video_status (single status check), 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 implies the tool should be used when the agent needs to block until a video task reaches a terminal state. However, it does not explicitly state when not to use it or mention alternatives like agnes_video_status for one-time checks, so guidance is only implied.

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