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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds key behavioral details: 'FPS exports return a resolved sampling summary and never regenerate the video.' This goes beyond annotations by describing side-effect-free behavior and the promise of returning a summary. However, it doesn't detail the consequences of quoting, such as whether it reserves resources or incurs costs. The description doesn't contradict annotations, so no contradiction flag.

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 long, front-loads the main purpose, and conveys the most important behavioral caveat (never regenerates the video) in the second sentence. It's concise and well-structured, avoiding verbosity.

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 a rich output schema (though not provided in the context, but it's stated to have one), and the schema details every parameter. The description covers the most critical behavioral aspect (FPS exports return a summary and don't regenerate). However, it doesn't mention the required source_video_asset_id ownership or the distinction from export_animation. Given the tool's complexity, the description could add a note about when to quote versus directly export, but the combination of schema and annotation provides enough context for an agent to call it correctly in most cases.

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 description doesn't directly explain parameters, but it hints at the FPS behavior ('FPS exports return a resolved sampling summary'), which relates to the fps parameter. The schema is extremely detailed, with descriptions for every parameter, so the description's contribution is minimal. However, since the schema coverage is 0% (meaning no description text), the description carries a small burden. The description's mention of FPS exports and the requirement for spritesheet and spritesheet_json (mentioned in the schema) is echoed but not expanded. Overall, the description adds a little value by hinting at the FPS-specific behavior, but the schema does most of the work.

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 operation: 'Quote an export from an owned source video.' It specifies the resource (owned source video) and the action (quote an export). However, it doesn't distinguish it from the sibling tool 'export_animation', which likely performs the actual export. The description does hint at a distinction by mentioning 'FPS exports return a resolved sampling summary and never regenerate the video,' but this is more behavioral than clarifying the tool's purpose relative to its siblings.

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 some guidance on when to use this tool (for quoting an export) but doesn't explicitly state when not to use it or how it differs from 'export_animation' or 'get_animation_export'. There's no mention of prerequisites, such as needing to own the source video or having a generation already done. The sibling list includes 'export_animation' but the description doesn't reference it, leaving the agent to infer the distinction. The description does mention that it 'never regenerates the video,' which is a hint for when to use it, but it's not sufficient for clear routing.

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