View frames

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 adds genuinely useful behavior: the return is images the agent can visually inspect, which is not in the annotations or schema. It omits practical constraints an agent would want, such as the 16-frame cap and the resolution/fidelity trade-off implied by width.

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 short sentences, front-loaded with the outcome (you get images) followed by the how. No filler, no repetition of schema constraints.

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 6-parameter tool with no output schema, the description covers the core interaction but leaves the count/width defaults and the likely interaction between times and count unstated. Adequate to call the tool, but an agent may need to open the schema to avoid passing conflicting parameters.

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 50%, so the baseline is 3. The description does add meaning beyond the schema by framing times and count as alternative sampling strategies rather than independent knobs, but the count default of 4 and the purpose of width are left entirely to the schema's bare constraints.

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?

"Returns video frames as images so you can see the content" gives a specific verb (returns), resource (video frames) and output modality (images). It does not distinguish itself from close siblings such as contact_sheet or keyframes, so an agent cannot tell from the description alone which frame-sampling tool to pick.

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?

"Give exact times, or a count of evenly spaced frames within start/end" tells the agent the two valid sampling modes, which is real usage guidance for parameterization. It stops short of saying when this tool is preferable to contact_sheet or keyframes, and gives no exclusions or prerequisites.

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