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

Beyond annotations, it discloses that the server computes all geometry, that the tool never starts paid generation, that dry_run defaults to true, and what apply requires. These are meaningful behavioral constraints not captured by the readOnly/idempotent/destructive hints.

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 purpose is front-loaded, but the description is a dense paragraph with several run-on clauses. Much of the content is useful, yet the structure makes it harder to extract the most important invocation rules quickly.

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 12-parameter, nested-object tool with no output schema, the description leaves substantial gaps. It does not explain the return value or result shape, and it covers only part of the complex scene schema, so an agent would still need to infer much from the input schema alone.

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 parameter meaning. It explains references, source_index, dry_run, draft_mode, request_id, and character_refs in part, but leaves many top-level and nested scene parameters undocumented, including duration_s, scene_id, title, camera, transition, model_key, model_values, continuity_from, project_id, expected_rev, music_evidence, and character_description.

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 states a specific verb and resource: build a multi-scene draft storyboard. It distinguishes itself from generic Canvas creation by saying it uses existing Canvas operations and computes geometry server-side, though it does not explicitly name sibling alternatives.

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 some important usage conditions: references must be explicit on every scene, coordinates must never be sent, dry_run defaults to true, and apply requires request_id with dry_run=false. However, it never states when to use this tool versus related siblings like canvas_create or canvas_preview.

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