select_window

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context by stating the return shape (counts by type and layer) and the 'visible objects' scope, but says nothing about whether the selection persists, how visibility/viewport affects results, or what happens with an empty box.

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?

A single front-loaded sentence that names the action, the scope, and the return content with zero filler. Nothing to trim.

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 8 parameters, 4 required and undocumented in the schema, no output schema, and a coordinate-mode ambiguity (px vs world) that materially changes results, the description is too thin. It never clarifies bbox ordering, whether coordinates are in image pixels by default, or the effect of the 'visible' constraint on returned counts.

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 38%; the four required bbox coordinates have no descriptions at all, and the description does not explain them either. It hints at type/layer filtering via 'counts by type and layer' but leaves coords (px vs world) and crossing semantics entirely to the schema's own field descriptions.

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: 'Box-select visible objects' plus what it returns (counts by type and layer). It is clear what the tool does, but it never distinguishes itself from close siblings like 'select' or 'find', which an agent could easily confuse it with.

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?

There is no when-to-use guidance, no exclusions, and no mention of the alternatives ('select', 'find', 'inspect') among the siblings. The only hint is the word 'visible', which implies a viewport dependency but is not explained.

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