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

Annotations only give readOnly=false/destructive=false/idempotent=false, so the description earns credit for disclosing project scoping, that the project identity is returned, and the non-obvious fallback that without a measured matte the preview shows a stand-in. It does not address repeat-call behavior or permissions, so it is strong but not exhaustive.

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 project-scoping constraint and the matte boundary before the dense kind list; every clause carries information. It is one long run-on paragraph of terse shorthand, which costs some scanability for an agent, but there is little filler.

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 15-param, nested-object, no-output-schema mutation tool, the description covers scoping, effect taxonomy, timing/trigger model, and matte prerequisites. Remaining gaps are secondary params (region, intensity, echo/style subfields) and whether it stacks with or replaces an existing subject effect.

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 only 40% schema coverage across 15 params, the description compensates heavily: it defines each kind's visual semantics (fill decays in 1-2 frames, poster colour=field, isolate keeps colour on scope with mono elsewhere, echo clones k frames back), the three timing forms, the on= trigger taxonomy split into speech clock vs added track, and count/per='shot'. This is meaning the schema enum labels alone cannot convey.

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+resource (adds an effect bounded by the person cut-out / subject matte) and enumerates the eight effect kinds it can produce, so an agent knows exactly what family of operation this is. It differentiates from siblings by scoping ('bounded by the person cut-out') and by explicit exclusions ('No sound, no zoom'), pointing away from add_sfx/add_zoom.

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?

"Earns its place on payoffs, structural beats and section changes, never decoration" gives an explicit when-to-use and when-not-to-use rule, and 'No sound, no zoom' rules out adjacent tools. It stops short of naming an alternative tool (e.g. add_region_effect) for non-matte effects, so it is clear context rather than full routing.

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