find_nodes

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

Annotations already declare readOnlyHint=true and destructiveHint=false, which the description does not contradict. The description adds valuable behavioral context: class matches both native and custom scripts (with the @Node@NN pitfall), name is substring-based, and path/recursive/max have defaults. It could have more explicitly stated the return format, but it does say 'returns their paths'.

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 description is three sentences, front-loaded with the primary purpose. The first sentence states the action and result, the second covers the class/name matching nuances, and the third lists parameter defaults. No filler words; every sentence earns its place.

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 read-only search tool with 5 parameters and no output schema, the description is complete. It explains all parameters, gives defaults, highlights a common pitfall (custom class_name nodes), and states the output's intended use with runtime_* tools. The agent has enough context to invoke it correctly.

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 0%, so the description must fully explain parameters. It does: 'class' matches native and custom classes, 'name' is a substring, 'path' is the scope root, 'recursive' is boolean, and 'max' caps results with default 100. Every parameter is given meaningful semantics beyond the bare 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?

The description uses a specific verb 'Find' with a clear resource: 'LIVE nodes in the RUNNING game'. It states the search criteria (by type and/or name) and the output (paths to feed into runtime_call/runtime_get_property/runtime_set_property). This clearly distinguishes it from static tree tools like get_scene_tree or get_remote_tree.

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 implies runtime usage by emphasizing 'LIVE nodes' and 'RUNNING game', and it names runtime_* tools as consumers. It also provides a critical usage nuance about custom class_name scripts, warning that is_class alone misses them. However, it does not explicitly mention alternative tools or when not to use this tool, so a 4 is warranted.

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