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

Annotations already declare read-only, idempotent, non-destructive, so the safety bar is low; the description still adds real behavior: a hard cap of twelve URLs versus four inline images, scene-relative array times, and the invariant that requested and actual image times are separate. The overlay-precompute requirement is genuine call-affecting context that annotations do not carry.

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?

Four short sentences with the output shapes front-loaded, no filler. Slight deduction for the telegraphic 'Requested and actual image times are always separate', which is compressed to the point of ambiguity about what the agent should pass.

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?

An output schema exists, so return-value explanation is rightly omitted, but with six undocumented parameters and zero required fields the description leaves a real gap: it never says whether `id` or `scene_id` (or neither) is needed, which is the main risk of a misinvocation.

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% across six parameters, so the description has to compensate and only partly does: it clarifies `limit`/`inline` via the twelve-vs-four bound, `at` via scene-relative times, and `overlay` via the precomputed-image rule. It says nothing about `id` versus `scene_id`, which selector to use, or what the 'key'/'transition_in'/'transition_out' enum values mean.

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?

States a specific verb and resource (get reference frames) and quantifies both output modes: up to twelve URLs or four bounded inline images. An agent can distinguish this from get_video/get_scene by the frame-level granularity, though no sibling is named explicitly.

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 or when-not-to-use guidance, and no alternative is named. The overlay sentence is a constraint, not routing advice, and the many sibling tools (get_text_track, get_scene, get_camera_track) are not distinguished.

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