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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description adds genuinely useful behavior: the call is project-scoped, never guesses the active-project pointer, and returns the project identity with the result. 'Merges into what it has' and 'clear=true restores the plain composite' also clarify that partial updates are non-destructive and reversible, consistent with the idempotent hint.

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 text is dense and telegraphic, with parenthetical asides ('fill_mode inside; field colours around them') and a long comma-linked list of blend behaviors that is hard to parse on first read. It leads with scoping rather than the core action, so it is not front-loaded. Most sentences do carry real semantics, so it is not padded, but structure could be much cleaner.

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 an 11-parameter mutation with no output schema, the description covers the semantically ambiguous options, notes merge behavior, the clear-to-restore path, project scoping, and that the result carries the project identity. The remaining gaps (opacity meaning, exact return payload) are minor relative to the complexity.

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 only 36% across 11 params, so the description must carry the load, and it does for the complex ones: blend gets per-enum semantics, fill gets inside/outside and field-colour behavior, plus ghost, stage, region and clear are explained. Gaps remain for opacity and field, and motion_id is only implied, so it falls short of full compensation.

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 conveys a specific verb+resource: it sets how a motion graphic joins the picture (MotionItem.composite), keyed to a motion_id within a project. It distinguishes itself from the add_* / set_motion_graphic siblings by framing the call as a composite/blend adjustment rather than creation. It lacks a single clean 'Sets X' opening sentence, which keeps it short of a 5.

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 description gives strong per-option guidance (difference for busy plates, screen/add for light, auto selects by measuring the plate, fill inside vs outside, ghost, stage screen under a camera move), which implies when each mode applies. However, it never states when to pick set_composite over related tools such as set_motion_graphic or set_overlay_motion, and there are no explicit exclusions.

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