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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description is not the sole carrier of safety information. It does add one useful behavioural fact — the affected material is derived from source images/frames and program windows rather than named explicitly — but it says nothing about whether the effect is additive over existing ones, whether it can be removed, or what confirmation the agent gets back.

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?

Two sentences, no filler, and the primary statement of what the tool adds is front-loaded ahead of the scoping remark. It is efficient; the brevity is a virtue, though it also reflects the under-documentation noted elsewhere.

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?

This is a 22-parameter, enum-heavy, nested-object mutation tool with no output schema, and the description covers only the kind dimension. Nothing explains the timing fields, the move object shape beyond the schema's one-line gloss, or the interaction between focus, rack_at and stage — leaving an agent with too little to invoke it correctly on the first try.

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?

With 22 parameters and only 23% schema description coverage, the description carries most of the documentation burden and does not meet it: it names the effect kinds but says nothing about move, focus/focus_from, strength, amount, density, blur, rack_at, stage, backdrop, colour, or the timing fields. An agent must guess at the nested move object and the many numeric knobs from bare parameter names.

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 gives a specific verb plus resource ('Adds a depth-based visual device') and enumerates the effect flavours (parallax, camera drift, DOF, rack focus, fog, light, point-cloud), which maps to the kind enum. It is clear what the tool produces, though it never names a sibling such as add_zoom or remove_depth_time to mark the boundary of where depth work ends and other effect tools begin.

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 or when-not-to-use guidance: nothing says to prefer this over add_zoom, add_subject_effect, or add_region_effect, nor what prerequisites (a loaded project, a placed clip) must hold. The only contextual line — that source images/frames and program windows determine the affected material — is a scoping hint, not selection guidance.

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