range_mask

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

It adds valuable behavior beyond annotations: it internally operates on a 'stretched gray copy', performs RangeSelection, and produces a new view via mask_id. It does not detail side effects or permission needs, but the annotations are not contradicted and the new-view statement implies non-destructive behavior.

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?

The entire description is one dense sentence that front-loads the core concept, parameter hints, and return value with no filler. Every part adds useful 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?

Given eight parameters, no output schema, no per-parameter schema descriptions, and only weak annotations, the description is adequate but has clear gaps: it omits id semantics and stretch, and does not explain the mask_id input/output ambiguity. It covers the core workflow, but not enough to fully specify a correct invocation without domain inference.

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 0% schema description coverage, the description partly compensates by specifying low/high ranges (0..1) and naming fuzziness, smoothness, and invert. However, the required id parameter is never explained, stretch is not mentioned, and mask_id is described as a return value even though it also appears as an input property.

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 identifies a specific resource ('Luminance range mask') and method ('RangeSelection on a stretched gray copy'), and states an output ('Returns mask_id (new view)'). It is clear enough to distinguish from star/pixelmath masks, but it lacks an explicit imperative verb such as 'Creates'.

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 phrase 'Luminance range mask' implies when the tool is appropriate, and the parameter list suggests selection by luminance values. However, it does not state conditions, prerequisites, or contrast with sibling mask tools like star_mask and pixelmath_mask, leaving the choice largely to inference.

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