Selecciones

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

No annotations are provided, so the description carries the full burden. It discloses useful behavior such as AI-based subject selection and that a selection can be chained into fill/clear/stroke/mask/deselect via "then", but says nothing about permissions, reversibility, coordinate expectations, or return behavior for what is clearly a mutating tool.

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?

Front-loaded with the purpose and then a compact keyword stream. It is dense and efficient, though it reads closer to a value dump than structured prose.

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 16-parameter, nested-object, no-output-schema, no-annotation mutation tool, the description is materially incomplete: it omits meaning for several params and gives no hint of the "then" sub-object's shape or result behavior.

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 19% across 16 params, so the description must compensate. It names most parameters by their value sets (type, mode, grow/shrink/smooth/border/feather, then) but adds no semantics for fuzziness, sampleAllLayers, points, radius, or the structure of "then", leaving real gaps.

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+resource ("Crea o modifica la selección") and enumerates the selection types, which lets an agent distinguish it from siblings like ps_mask or ps_fill. It stops short of true differentiation language, but the purpose is unmistakable.

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 lists the available modes and post-actions but never says when to choose one type over another, nor when this tool should be preferred over ps_mask or ps_fill. It is a value enumeration rather than usage guidance.

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