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 adds important context that the tool monitors the subprocess rather than the Gemini API directly, and that the subprocess handles API polling. It does not detail potential edge cases like subprocess failure or return behavior, but the output schema likely covers return structure, making this sufficient for a status-check 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 concise and front-loaded, with the core purpose in the first sentence. Each subsequent sentence adds distinct value: clarifying the subprocess architecture and mentioning the alternative tool. 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 status-check tool with one parameter and an output schema, the description provides sufficient context. It explains the tool's role in the generation workflow, how it relates to the API, and when to choose an alternative. The return values are presumably covered by the output schema, so no further description is needed.

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 already provides 100% parameter coverage, including the description 'Session ID returned from veo_generate_video.' The tool description adds no further parameter semantics beyond the schema, so the baseline score of 3 applies.

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

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

The description opens with 'Check the status of a video generation subprocess,' using a specific verb and resource. It clearly distinguishes this tool from direct API queries by explicitly stating 'not the Gemini API directly' and contrasting with veo_check_operation.

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 when to use this tool versus the alternative: 'This monitors the subprocess... If the generation has an operation_id, you can also use veo_check_operation to directly query Google's API.' This gives explicit usage context and a named alternative.

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 that it removes state files and optionally downloaded videos, which is useful, but it does not warn about irreversibility or mention filtering behaviors like 'completed_only' or the age threshold. This is moderate transparency but lacks depth for a destructive operation.

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

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

The description is two sentences, front-loaded with the main purpose, and every word earns its place. It is concise, clear, and well-structured.

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 the core behavior and the output schema handles return values. It does not mention irreversibility or the exact filtering criteria, but for a simple cleanup tool with fully documented parameters, it is adequately complete. A warning about permanence would elevate it further.

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 documents both parameters fully (100% coverage), so the baseline is 3. The description adds some context by mentioning 'state files' and 'downloaded videos', but it does not explain the parameters directly or add meaning 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 clearly states the verb 'clean up' and the resource 'generation sessions and their files', distinguishing it from sibling tools like 'veo_list_sessions' and 'veo_download_video'. It is specific and 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 clear context for when to use this tool (old sessions cleanup) and implicitly contrasts it with list/download tools. However, it does not explicitly mention when not to use it or name alternative tools, so it stops short of a 5.

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 full responsibility for behavioral disclosure. It transparently notes the SDK limitation that downloads placeholder data and that the actual API requires allowlist access. It also lists return fields (file_path, file_size, success), giving the agent a clear picture of expected output. Could add more details about failure cases, but the key caveat is well covered.

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 sections: main purpose, usage bullets, caveat, and return values. It is slightly verbose because the 'Use this tool to' list partly repeats the opening sentence, but every section adds useful context, and the critical placeholder-data caveat is effectively highlighted.

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

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

The tool is moderately complex, involving a download operation with a major SDK limitation. The description covers the essential context: when to use it, what it returns, and the placeholder-data restriction. The output schema also helps, reducing the need for the description to explain return values in full. It does not cover error handling or prerequisites like session completion, but the sibling tools and schema infer most of this.

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%, so the input schema already documents all three parameters with descriptions. The tool description adds no parameter-specific meaning beyond reinforcing that video_index relates to multiple samples, which is already implied by the schema's 'Index of the video to download' text. The baseline of 3 applies because the schema does the heavy lifting.

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 downloads a generated video from a completed generation session, using the specific verb 'Download' and resource 'video'. It distinguishes from sibling tools by listing specific download-related use cases (downloading after generation, selecting from multiple samples, re-downloading).

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

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

The description provides clear context for when to use the tool via a bulleted 'Use this tool to' list, covering common download scenarios. It does not explicitly state when not to use it or point to alternatives, but the sibling tool names (e.g., veo_check_generation) make the intended use evident.

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 full burden. It discloses the asynchronous nature ('starts a background video generation process'), returns (session_id, status, pid), and model-specific constraints (image-to-video only Veo 3). It does not mention rate limits or failure modes, but the critical behavioral traits are covered.

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 headings and bullet points, making it scannable. Each section (Supports, workflow, Returns, Examples) adds unique, non-redundant information, and there is 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?

Given the tool's complexity (14 parameters, async workflow), the description covers the full lifecycle: generation, monitoring via session_id, and download via veo_download_video. It names companion tools, explains return values, and provides examples. It is self-sufficient 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?

The schema has 100% parameter coverage, so baseline is 3. The description adds value beyond the schema by explaining how prompt and image_path combine for the three modes, providing a concrete example ('Serene waterfall in a lush forest, cinematic lighting'), and noting that image_path is Veo 3 only—a constraint not fully explicit in 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 'Generate videos using Google's Veo models,' a clear verb+resource statement. It further distinguishes itself from sibling tools (veo_check_generation, veo_download_video) by being the generation entry point and enumerating the three supported modes (text-to-video, image-to-video, both), making its scope 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 clear workflow context: 'This tool starts a background video generation process' and directs users to 'use veo_download_video after generation completes' and reference veo_check_generation for monitoring. This explains how the tool fits into the pipeline, though it does not explicitly state when not to use it or name alternative generation tools.

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 burden of behavioral disclosure. It states 'List all...' which implies a read-only operation and mentions 'current status' as output, but it does not explicitly note that it is non-destructive, nor does it mention any side effects, permissions, or limitations. The addition of 'subprocess-based' gives some context but not enough to rate higher.

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 extremely concise: two sentences, with the primary action front-loaded in the first sentence. No filler or redundant information 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 is simple with one well-documented parameter and an output schema. The description clarifies what is listed (all subprocess-based generation sessions) and that status is shown. However, it lacks a note distinguishing it from the similar sibling veo_list_sessions, which would improve 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?

The input schema provides a full description for the only parameter, active_only, so schema coverage is 100%. The tool description does not add any parameter semantics beyond the schema, meeting 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 uses a specific verb 'List' and identifies the resource as 'video generation sessions', further specifying 'subprocess-based generation sessions' which clearly distinguishes it from siblings like veo_list_sessions and veo_check_generation.

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 explicit guidance is given about when to use this tool versus alternatives such as veo_list_sessions or veo_check_generation. The intended usage is only implied by the name and the act of listing sessions.

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 explaining behavior. It adds useful detail about subprocess-based sessions and status display, but does not explicitly state read-only nature, potential side effects, or required setup. For a list operation, the transparency is adequate but not comprehensive.

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

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

The description is two concise sentences, front-loaded with the main action, and every sentence contributes relevant information. There is no wasted wording.

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 low complexity (one optional parameter) and the presence of an output schema, the description sufficiently specifies the tool's function and output. It could clarify the difference from list_generations, but that is not essential for correct 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?

The schema fully documents the single parameter active_only with its description and default value, and the tool description aligns with that default behavior of listing all sessions. The description adds no additional parameter semantics 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 clearly states the tool lists all video generation sessions with the verb 'List' and a specific resource. It adds 'subprocess-based' and 'current status' to clarify scope, but does not explicitly distinguish from the sibling veo_list_generations, so it lacks explicit sibling differentiation.

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 no guidance on when to use this tool versus alternatives like veo_list_generations, and no exclusions or prerequisites are mentioned. It simply states the action without giving contextual usage information.

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