find_instances

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

With no annotations, the description must carry the behavioral burden. It discloses scope (whole game) and a performance trait (faster than a full scene dump), which is useful, but says nothing about return format, whether paths/parents are included, result ordering, or the pagination limit behavior that the 500-cap suggests matters.

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 tight sentence plus a concrete example, front-loaded with the core purpose and followed by the performance motivation. No filler or redundancy.

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 4-parameter, no-output-schema search tool, the description covers the intent but omits what a caller receives (list of instances? paths? structured objects?) and how to page past the default 100 hits. Those are meaningful gaps when no output schema exists.

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 100%, so root, limit, className, and nameContains are already fully documented in the schema, including defaults and the max of 500. The description echoes name/class filtering but adds no semantic detail (e.g., how root interacts with className) beyond the schema.

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 (search) and resource (instances across the whole game) plus the two filter dimensions (name and/or class). It implicitly distinguishes itself from scene-dumping siblings via 'faster than dumping the full scene,' though it never names get_scene or get_children explicitly.

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?

Provides an example use case ('all Scripts with Boss in the name') and a comparative hint against dumping the scene, which implies when to prefer it. However, no alternative tool is named and there is no explicit when-not-to-use guidance.

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