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

Annotations already flag this as a destructive, non-read-only, idempotent write, and the description adds real context beyond them: revision checking, no paid generation cost, and core-side rejection of ambiguous scenes. It does not spell out what the destructive overwrite replaces (prior prompt text) or what an ambiguity error looks like.

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 tight sentences, with the mutation/non-generation constraint front-loaded and the prerequisite second. No filler, and both clauses carry actionable content.

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?

Return values need not be explained because an output schema exists, and the description covers the risk profile and identifier sourcing for a destructive write. The one gap is partial-update behavior when only one of board_prompt or video_prompt is present, which the anyOf schema permits.

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?

With 71% schema coverage the schema already documents most parameters, yet the description adds meaning the schema lacks: where scene_id and clip_id come from (get_project) and that expected_revision is a staleness guard. It says nothing about request_key reuse semantics or how board_prompt versus video_prompt are treated when only one is supplied.

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: saving literal Board/Video prompt edits on an exact native clip. It also explicitly delimits what it is not ('no model rewrite or paid generation'), which separates it from generation siblings like generate_scene_media and revise_scene.

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?

Gives a concrete prerequisite path: read get_project to obtain scene_id and clip_id, and warns that core refuses ambiguous scenes. It does not explicitly name the alternative tool to use when a model rewrite or paid generation is actually wanted, so the when-not is implied rather than routed.

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