Render frame

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

Annotations only provide destructiveHint: false, while the description goes far beyond that, detailing headless deterministic rendering, color-managed transforms via OCIO, fallback paths to ACES or raw values, and the response's colorPipeline/colorWarning indicators. This gives deep behavioral insight.

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?

Opens with a clear purpose statement, then a usage note, followed by essential technical details. Every sentence contributes substance—there's no filler or repetition. The structure moves from simple to complex, making it easy to parse.

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 rendering tool with no output schema, the description fully covers what the tool does, when to use it, how it behaves (including color management), what the output looks like (sRGB-tagged vs raw), and what to look for on the response (colorWarning). It also addresses edge cases like read-only mode and missing OCIO effect.

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 already provides thorough parameter descriptions (100% coverage), so the baseline is 3. The description adds extra semantic context by explaining the color-managed behavior in detail, particularly for the colorManaged parameter, and mentioning the effect of working space, which enriches understanding 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?

Clearly states 'Render a single frame to PNG' with a specific verb, resource, and output format. It also frames its purpose as 'the agent's eyes' for visual verification, distinguishing it from sibling tools like ae_project_info or ae_save_project.

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 instructs 'Use to visually verify edits' and recommends pairing with mutations for a visual feedback loop, providing strong contextual guidance. It doesn't explicitly list alternatives or exclusions, but the use case is unambiguous.

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