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

Annotations already cover the read-only, non-destructive profile, and the description adds real context: it is project-scoped (acts only on explicit project_id, never the active-project pointer), checks candidates against intensity budget, flash safety and restraint rules, and reports that zero candidates is acceptable. It does not contradict the annotations.

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?

Front-loads the two most decision-critical facts (PROJECT-SCOPED, READ) and every sentence carries weight about scope or process. It is a single dense paragraph with heavy parentheticals that slightly impede parsing.

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 steps in to describe the return shape (ranked candidates each bound to a moment and carrying an apply_edit_batch operation) and the intended follow-up workflow. Given 57% schema coverage, a few parameter details remain undocumented, but the operational picture is complete.

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?

At 57% schema coverage across 7 params, the description clarifies project_id scoping, ties 'intensity' to the budget concept, and explains the 'asked' behavior (no zoom/sound unless asked). It leaves families, max_candidates, start and end to the schema, so it adds only partial meaning over structured fields.

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 (suggest) and resource (ranked creative-device candidates) and enumerates the exact families it draws from (silhouette flashes, punctuation frames, junctions, grade windows, finishes, type behind the subject). An agent can distinguish this from suggest_emphasis/suggest_motion_beats/suggest_recipes by the explicit content scope.

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?

Gives clear workflow guidance: pick the ones that serve the story, write them in ONE apply_edit_batch, then proof_device them. It also sets a boundary ('never proposes a zoom or a sound unless asked; zero candidates is a fine answer'). It stops short of explicitly naming the sibling suggest_* tools and the condition that selects them.

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