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

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false) by disclosing optimistic-concurrency semantics, conflict resolution ('Conflicts preserve the newer saved version'), and the input contract ('HTML, JS, CSS and URLs are not scene inputs'). It also clarifies that no language model is invoked, which is useful non-obvious behavior. It stops short of stating permission requirements or error/failure modes.

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 tight sentences, front-loaded with what is saved, then inputs accepted/rejected, then the revision lifecycle. Each sentence earns its place with no filler. Slightly dense jargon (MotionSceneV1, Brix36) is the only cost.

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?

An output schema exists, so return values need not be described, and the description covers the mutation lifecycle, concurrency, and input constraints for a non-idempotent write tool. Remaining gaps are auth/permission expectations and failure behavior, which are minor against the covered ground.

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 description coverage is 0%, so the description must carry the load, and it partially does: it explains documentId (created opaquely on first save) and expectedRevision (bound on edits), which the bare schema does not convey. projectId is never addressed and 'scene' is characterized by content rather than structure, so two of four parameters remain thin.

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+resource: 'Saves typed MotionSceneV1' and enumerates the scene content (words, cue frame ranges, asset IDs). It implies the create-vs-update behavior via the documentId/revision rule, but never names sibling alternatives such as studio_motion_create or studio_motion_read, so differentiation is inferential rather than explicit.

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?

The sentence 'First save creates an opaque documentId with expectedRevision 0; edits bind the current expectedRevision' effectively describes the two usage modes and their preconditions. However, it does not say when to prefer this tool over siblings (e.g., studio_motion_create, studio_motion_restore) or what to do outside the happy path, so usage is implied rather than guided.

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