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

Annotations already declare readOnly=false, idempotent=false, destructive=false and openWorld=false, so the safety profile is covered. The description adds genuine context beyond that — matte weighting, an option for affecting type, and "flash checks apply to luminance changes" — but the last phrase is undefined jargon and there is no statement about permission needs, what happens on repeated adds (relevant given idempotent=false), or interaction with existing finishes.

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 dense sentences, front-loaded with the action and the finish catalogue, with no filler. It loses a point only because clauses like "flash checks apply to luminance changes" are compressed to the point of being ambiguous rather than informative.

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-parameter mutation tool with a nested region object, three enums, and no output schema, this description is thin — it should have sketched the windowing parameters and the region/strength/palette mechanics. Annotations cover only the safety profile, so the description is the sole source for invocation semantics and it does not supply enough.

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 40% across 15 parameters, so the description carries a heavy burden and largely fails it: it touches matte_weighted and the type-affecting option, and "windowed" loosely implies start/end/ramp_in_f/ramp_out_f, but region, palette, strength, direction, scale, origin, stage, and the nested FxRegion object get no explanation at all. Notably, stage's enum value over_type (the mechanism behind "affects type") is never connected to the description's phrasing.

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?

"Adds a windowed picture finish" is a specific verb+resource, and the enumerated examples (halftone, xerox, film, thermal, line-art) map directly onto the kind enum, so an agent knows exactly what gets created. It stops short of distinguishing itself from adjacent creative-effect siblings such as add_stylize, add_custom_filter, or add_color_screen, which is the only thing keeping it from 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?

Usage is only implied: "windowed" hints this is a timed effect layered over a range, but there is no explicit when-to-use or when-not-to-use guidance, no mention of a removal counterpart (remove_finish exists as a sibling), and no condition separating it from add_stylize or add_custom_filter. The agent must infer selection from the example finish names alone.

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