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

Annotations already declare this is a non-readonly, non-idempotent, non-destructive write, so the description only needs to add beyond that. It does: it discloses that without a measured matte previews fall back to a stand-in, that timing can be driven by measured events, and that no audio or zoom is produced. It stops short of saying what happens when kind conflicts with the available matte or how the effect is layered/stacked.

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?

Three sentences, front-loaded with the core concept before timing and fallback details. The effect enumeration is long but earns its place by mapping to the kind enum. Minor density, but no filler or repetition.

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, nested-object mutation with no output schema, the description covers the concept, timing model, and fallback behavior but leaves the agent without guidance on the many styling/spatial parameters (region, style, scope, intensity) and on where the effect lands in the timeline. Adequate as a concept statement, incomplete as an invocation guide.

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 40% across 15 parameters (including nested style, echo, and region objects), so the description carries real burden. It does add meaning for kind (the effect list) and for start/end/on (explicit windows vs. measured events), but it says nothing about scope, per, intensity, count, frames, hue, colour, region, or style. Roughly half the parameter surface remains unexplained by either schema or description.

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 opens with a specific verb and resource: 'Adds an effect constrained by a measured subject matte,' and enumerates the concrete effect kinds (fill, poster, glow, outline, negation, isolation, echo) that map to the kind enum. It also carves out scope with 'adds no sound or zoom,' which separates it from add_sfx/add_zoom siblings. It does not explicitly distinguish it from the closest sibling, add_region_effect, which keeps 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 context is implied rather than stated: the tool is for matte-constrained subject effects, and 'Timing can use explicit windows or measured events' hints at two invocation modes. However, there is no explicit when-to-use/when-not guidance and no named alternative (e.g., add_region_effect or isolate_colour) for cases where no measured matte exists. An agent must infer selection from the sibling list.

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