evaluate_frame

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds that evaluation returns property values rather than rendered pixels, clarifying cost/behavior. It is silent on what session or scene state is required (sessionId appears in the schema but not the text), whether evaluation mutates cached runtime state, and whether omissions in `parameters` fall back to stored values.

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?

Two front-loaded sentences with no filler: the first states the evaluation surface, the second states the return contract. Nothing is wasted, though the second sentence could have been spent on differentiation instead of what the name partly implies.

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 six-parameter, nested-object, no-output-schema tool with zero schema descriptions, the definition is underspecified: no parameter explanations, no indication of defaults for an all-optional schema, and no disambiguation from the near-identical `evaluate_at_time` sibling. The lack of an output schema means the return shape ("property values") is left vague, so more detail was warranted.

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% for six parameters, including a nested free-form `parameters` object, so the description must carry the burden and largely fails. "At a requested time" loosely maps to timeMs and "runtime parameters" maps to `parameters`, but `requestId`, `sessionId`, `timelineIds`, and `expectedRevision` receive no explanation at all — including the important concurrency/versioning meaning of expectedRevision.

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 gives a specific verb ("Evaluate") and names the resources involved (timelines, bindings, parameter wiring, runtime parameters) plus the output class (property values, no pixels). However, the sibling list contains `evaluate_at_time`, whose name and implied purpose are nearly identical, and the description does nothing to separate the two. An agent cannot confidently pick between them from this text.

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?

There is no when-to-use guidance, no when-not-to-use, and no mention of alternatives such as `evaluate_at_time`, `get_scene_json`, or `render_preview`. The only implicit cue is "without rendering pixels," which hints at a lightweight path but never states the condition that selects it over the render/export siblings.

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