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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=false, but the description adds genuinely new behavior: expectedRevision-based optimistic concurrency, retry reconciliation via a stable operationId, and the fact that there is no model call or credit charge. It stops short of saying what a revision conflict returns or whether the replacement is reversible.

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?

Three dense, front-loaded sentences; the core action comes first, then the edge case, then the concurrency/idempotency contract. Nothing is padded.

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, revision-guarded mutation with an output schema (so return values need no prose), the description covers idempotency, the revision precondition, scoping, and cost. The only missing piece is explicit routing versus sibling write tools.

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 only 50% schema description coverage, the description compensates by explaining the sceneIndex null case and the text coupling, and by tying expectedRevision to savedPlan.revision from studio_film_read. The text and referenceAttachmentIds parameters get only indirect treatment, which leaves a small gap.

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 (Replace) and resource (one scene's direction and reference pictures), and further scopes the special case where a null sceneIndex binds whole-Film references. An agent can distinguish this from studio_film_scenes_write or studio_film_script_write without opening their schemas.

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 clarifies the null-sceneIndex/empty-text condition for whole-Film binding, which implies scope selection, but never states when to prefer this tool over sibling writers like studio_film_scenes_write or what happens on revision mismatch. Usage is inferable rather than explicit.

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