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

Annotations already declare the write/non-idempotent/non-destructive profile, so credit goes to added context: the call is project-scoped, validates the LUT (65^3 cap), and returns the project identity with its result. It does not say whether repeated calls stack or replace an existing grade, which is the main residual gap.

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, with the PROJECT-SCOPED constraint front-loaded before the operation itself. Every clause carries operational information.

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 and only 50% schema description coverage, the description supplies the return value (project identity), source alternatives, range semantics, strength bounds, and validation limits. Nothing needed to invoke the tool correctly is missing, aside from edge behaviour on repeated application.

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 50% schema coverage the description meaningfully compensates: it maps asset_key vs url as alternative sources, clarifies start/end as a half-open time range (the schema's 'program s' text is cryptic), and bounds strength to 0-1. It still omits start/end units and strength's default.

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?

Names a specific verb and resource ('Apply a .cube LUT') plus the defining constraints (65^3 max, validated, applied over [start, end) at strength 0-1). The artifact type distinguishes it from look/recipe/grade siblings such as apply_look, apply_recipe and set_color_grade without needing to open any schema.

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?

The description implies usage conditions (LUT pulled from a project asset or a URL, applied across a time range) but never states when to reach for this over the colour siblings (apply_look, match_grade, set_grade_custom) or what prerequisites exist. Usage is inferable rather than stated.

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