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

Beyond annotations, the description discloses important behavior: saving a playable project, refusal of unsupported changes without rebuilding, retry/idempotency handling via operation_id, use of the account's direct-edit allowance, and that the operation is free. These details materially help an agent call it correctly.

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 front-loaded with the core action and then adds only operationally relevant details: prerequisites, project saving, refusal behavior, retries, allowance, and cost. Each sentence carries useful information with no filler.

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 100% schema coverage, output schema, and destructive/idempotent annotations, the description covers the key prerequisites, side effects, retry behavior, cost, and separate file retrieval. An agent has enough context to invoke it correctly.

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 100%, so the baseline is 3, but the description adds workflow meaning by tying base_version and output_id to get_project_context and by reinforcing operation_id preservation on retries. It does not add much about the nested screen object, but the schema already documents that.

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 names a specific verb and resource: replacing a scene screen with the supported screen shape from get_project_context. It is clear enough for an agent to identify the operation, though it does not explicitly distinguish it from nearby tools such as swap_scene_picture or add_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?

It gives clear workflow guidance: read get_project_context first, pass base_version and selected output_id, and use check_video with_download to request a file separately. It also notes that unsupported changes are refused, but it does not explicitly compare this tool against sibling editing tools beyond the download alternative.

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