find_error_nodes

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

With no annotations, the description carries full burden and does so well: it explains the single-call allSubChildren() collection, the dual return lists, truncation behavior for max_warnings, and default semantics for include_warnings and max_errors.

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 concise and front-loaded with the purpose, followed by implementation details and a use case. The reference to 'PR 11' adds some internal jargon but does not significantly detract.

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 scanning tool with no output schema, the description covers the return structure and key behaviors. It does not specify the format of individual error/warning entries, but otherwise is fairly complete.

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?

The description adds meaning to root_path, include_warnings, max_warnings, and max_errors, including defaults and truncation flags, despite zero schema coverage. However, the required ctx parameter is not explained, leaving a minor gap.

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 clearly states it scans error and warning nodes in the scene, which is a specific verb+resource. It distinguishes itself from siblings like find_nodes and cook_node by focusing on errors/warnings and returning categorized lists.

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?

It provides a clear use case: 'suitable for one-time health check after scene construction' and compares to cook_node as slower. However, it does not explicitly state when not to use it, such as for targeted per-node debugging.

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