armorpaint_select_object

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

Annotations already show the operation is not read-only and not destructive; the description adds that the identity comes from get_state. It doesn't explain side effects like replacing the current selection or invalid-index behavior, but those are largely implied by a simple select operation.

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?

One sentence of a dozen words conveys the action, target, and data source, with no filler or repetition of the schema's type/minimum details.

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?

The tool is low-complexity (one required integer parameter) and has an output schema, so the description covers the essential call contract. Minor ambiguity remains about the exact get_state field and behavior on an out-of-range index, but not enough to materially impair use.

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 coverage, the description must do the work, and it does: it explains that index is zero-based and that a valid value comes from get_state. It could be more specific about which get_state field/array to read, but for a single integer parameter the semantic guidance is strong.

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 an explicit verb ('Select'), a concrete resource ('a mesh'), and the selector semantics ('zero-based index returned by get_state'). This is enough for an agent to distinguish selecting an object/mesh from selecting materials or layers among the siblings.

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 'returned by get_state' gives a clear workflow precondition: call get_state first and then use the generated index. It doesn't mention alternatives such as set_object or when not to use it, but the intended usage context is clear.

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