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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower, yet the description adds real substance: project scoping, that the project identity is returned with the result, the freshness-discounted ranking policy, the per-result payload (word, why, exemplar, ops), and the aesthetic guarantee 'silent, zoom-free, flash-safe'. This is materially more than the annotations convey. It does not explain result count limits or whether start/end scope the analysis.

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?

It is front-loaded with the useful PROJECT-SCOPED and READ labels, which is good practice. However the body is a long, jargon-dense enumeration of 13 move names with parenthetical re-explanations that occupies most of the text; for a suggestion tool whose output itself names the moves, this list is largely overhead that dilutes the actionable information.

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?

With no output schema, the description correctly carries the return-value burden, describing the shape of each suggestion (word it lands on, why, exemplar, apply_edit_batch ops). It also discloses scoping and ranking. The remaining gap is the undefined start/end/max_results parameters, which an agent needs in order to bound the call.

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 only 25% (only project_id is documented, and its schema text is already thorough). start, end, and max_results are undocumented in both schema and description. The description never tells the agent that start/end scope the cut or what max_results controls, so it fails to compensate for the coverage 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?

The description names the resource (creative MOVES/recipes a cut earns) and enumerates the actual move types, so an agent knows this is a suggestion engine for editorial visual moves. It is distinguishable from apply_recipe/apply_edit_batch because it states it returns the moves plus the exact apply_edit_batch ops rather than executing them. It never states a plain verb like 'suggest' — the purpose is conveyed through output description and heavy domain jargon, which is clear but indirect.

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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. It never points to apply_recipe, apply_edit_batch, or the sibling suggest_* tools (suggest_devices, suggest_emphasis, suggest_motion_beats), even though these overlap. The only contextual rule given is a ranking property ('a move the other shorts of the same batch used ranks lower'), which is behavior, not tool selection.

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