get_file_references

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

With no annotations, the description carries full burden. It mentions output includes 'the parameter holding it and whether it exists', which is useful. However, it doesn't disclose whether the tool performs disk I/O beyond checking existence, performance implications for large scenes, or if it can be called without side effects. It does not contradict annotations (since none exist), but the behavioral disclosure is thin.

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 main purpose. The Args section is also brief. But it includes the formal 'Args:' block that repeats param info already in the schema, which is somewhat redundant. It's acceptable but not perfectly lean.

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?

Given a single optional parameter and no output schema, the description could be more complete. It doesn't describe the response format (e.g., list of paths, grouped by parameter, missing vs existing). However, for a simple list tool, it covers the core purpose. With no annotations, more detail on behavior and output would improve completeness.

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 description coverage is 0%, so the description must explain parameters. It does explain 'include_missing_only: Only report paths that are missing on disk', which adds meaning beyond property name. However, it doesn't clarify default behavior (false) or the semantics of the returned structure. The description adds minimal value.

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 lists every file path the scene references, with the parameter holding it and whether it exists. This is a specific verb (get/list) and resource (file references), distinguishing it from generic list tools. However, it doesn't explicitly differentiate from siblings like get_geometry_info or get_attrib_values, though the resource is distinct enough.

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 implies when to use: when you need to know referenced file paths and their existence. But it doesn't state when not to use or alternatives, such as for checking cache paths or other reference types. There is no explicit guidance on selecting this over sibling tools.

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