Video Frame

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

With annotations provided the bar is lower, and the description does add genuine behavioral context: times are relative to the measured container presentation origin, precise selection returns the first decoded frame at or after the request, and keyframe selection reports its approximation and method. However it does not explain why readOnlyHint is false for what reads as a pure retrieval operation, nor does it mention decode cost, caching, or any side effect an agent should know about.

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?

Three short sentences, front-loaded with the core action and with no filler. The phrasing is dense and slightly jargon-heavy ('original decoded PTS', 'actual delta'), but nothing is wasted.

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 values need not be described here. All six parameters are documented in the schema, and the description covers the two facts an agent cannot get from structured fields alone: the time reference origin and what each selection mode actually returns.

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 baseline is 3. The description reinforces the meaning of time_seconds (relative to the measured container presentation origin) and elaborates the selection enum's return semantics, but adds little about crop_box, max_pixels, or include_image beyond what the schema already states.

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 a specific verb+resource pair ('Retrieve a source frame') and immediately scopes it to a requested time, which cleanly separates it from bulk siblings like video_frames and video_storyboard. It never names an alternative, so the differentiation is implicit rather than explicit.

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 statement and no reference to the obvious siblings video_frames, video_frame_by_query, video_detect_scenes or video_storyboard, which an agent must choose between. The precise-vs-keyframe explanation describes behavior of a mode rather than advising when each mode is appropriate (e.g. speed vs accuracy tradeoff).

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