video_visual_transform_plan

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

With no annotations, the description bears full burden. It mentions 'plan' and 'crop budgets' but does not disclose whether the tool is safe, modifies state, requires permissions, or what the plan object contains. Essential behavioral traits are missing.

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?

The description is very concise—one sentence. While efficient, it sacrifices necessary detail for a planning tool with complex inputs. It earns a middling score for minimalism at the expense of completeness.

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?

Given the flexible input schema and the existence of an output schema (not shown), the description is insufficient. It does not explain the request structure, return value, or how to integrate the plan with other tools, leaving critical gaps.

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 single 'request' parameter is an object with additionalProperties: true, and schema coverage is 0%. The description does not explain what keys or values the request expects, providing no added meaning beyond the raw 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?

The description clearly states the tool plans subject/camera analysis, reframing, or stabilization with crop budgets, differentiating it from direct execution tools like video_crop and video_stabilize. However, 'plan' is somewhat vague, and the specific output of the plan is not described.

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?

No guidance is provided on when to use this tool versus alternatives like video_crop or video_stabilize. The description does not suggest prerequisites, context, or exclusions, leaving the agent to infer usage.

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