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

Annotations already declare the safety profile (not read-only, idempotent, non-destructive, closed-world), so the description only needs to add context. It does add useful behavior: the controls are continuous and adjust relative to an existing grade, and ranges are bounded. But it never says whether omitted controls stay untouched, whether the grade is scoped to the whole project or a range, or what the mutation returns.

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, front-loaded with the action and its placement relative to the preset grade, with no filler. The second sentence is densely packed and slightly hedged ('and other controls have defined ranges'), but nothing is redundant.

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 an eight-parameter mutation with no output schema and near-zero schema documentation, the description establishes the essential framing (continuous controls layered on a preset, delta-vs-multiplier semantics) but leaves the caller without concrete ranges or units and without knowing the effect of leaving parameters unset. The reference to schema-documented neutral values, which do not exist, is the main completeness defect.

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 13%, so the description must carry parameter meaning, and it does clarify an important ambiguity: contrast and saturation take signed deltas or explicit multipliers rather than absolute values. However, four of the eight parameters (tint, shadows, highlights, plus the unspecified 'other controls') get no explanation at all, and it defers to the schema for 'neutral values' and ranges that the schema does not actually document — a misleading pointer for a caller trying to pick sane numbers.

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?

States a specific verb and resource: 'Adjusts continuous footage color controls after the preset grade.' The phrase 'after the preset grade' implicitly positions it downstream of set_color_grade and distinguishes it from preset-application tools. It never names a sibling, however, so an agent must infer the boundary against set_color_grade, match_grade, apply_look, or set_intensity itself.

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 through 'after the preset grade,' which hints this is a follow-on customization step rather than a standalone grading call. There is no explicit when-to-use instruction, no statement of prerequisites, and no exclusion naming what to use instead for preset-level grading or for windowed grades (set_grade_window).

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