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

Annotations already cover read-only and idempotent behavior, but the description adds genuinely new context: unsaved changes are not reflected, no export allowance is consumed, and the design is not modified. It does not describe the response payload (e.g. URL vs inline PNG), which is the remaining behavioral gap.

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, front-loaded with what the tool does, followed by selection modes, defaults, and the safety/persistence caveat. No sentence 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?

With no output schema, the description carries the return-value burden and says only 'as PNG' without indicating whether the result is a URL, binary, or reference. Everything else an agent needs to pick a frame is present.

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 coverage is only 38%, so the description needs to compensate; it does so for the two selection modes, explaining that a visible scene index plus relative position is one option while an absolute 30-fps frame is the other. It also notes the format defaults to the preview format. It says nothing about the interaction between 'at' and 'frame' when both are supplied, nor about scale or variantId.

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 ('Renders one frame of a saved promo video as PNG') plus the use case ('for inspection'). This clearly separates it from export_promo_video, generate_promo_video, and get_promo_video.

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?

Says it is for inspection and that it 'does not consume export allowance or modify the design', which implicitly routes the agent here rather than to export_promo_video. It does not name the export sibling explicitly, so an agent must infer the exclusion.

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