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

Goes well beyond the destructiveHint/idempotentHint annotations: it discloses that footage time is destroyed, that the result is a saved playable project rather than a file, that unsupported changes refuse without rebuilding, that operation_id and exact inputs must be preserved on retries, that it consumes the account's direct-edit allowance, and that it costs no credits.

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?

Purpose is front-loaded and each sentence carries operational value (alternative, prerequisite, output, failure mode, retry, quota, cost). It is dense and slightly crammed into one paragraph, but there is 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?

For a destructive mutation with an output schema and annotations already covering safety, the description supplies everything else an agent needs: prerequisite call ordering, version pinning, idempotent retry protocol, quota/cost impact, and failure behavior.

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 already 100%, so baseline is 3; the description adds cross-tool provenance for base_version/output_id and stresses retry semantics for operation_id. Slight ambiguity: it says output_id comes from get_project_context while the schema attributes it to check_video, which could confuse a careful agent but is not harmful.

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 ("Remove this scene and its footage time") and immediately names the closest sibling (remove_scene_layer) with the distinction between full-scene removal and layer-only removal. An agent can differentiate it from add_scene/move_scene without inspecting any schema.

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 explicit when-to-use vs. alternative ("To remove only graphics or camera motion while keeping speech, use remove_scene_layer"), plus a mandatory prerequisite sequence (read get_project_context first, pass base_version and output_id) and follow-up routing (request a file via check_video with_download).

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