scan_export_folder

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

With no annotations provided, the description carries the full burden. It discloses that the tool runs locally, does not connect to UE5, and returns a manifest rather than performing an import. It does not explicitly state 'read-only' or 'non-mutating,' but the scanning/preview framing strongly implies no side effects.

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 well-organized with Args, Returns, KB, and Example sections, and every section serves a purpose. However, the contradictory example is a structural flaw – it is actively misleading. The length is acceptable, but the incorrect usage example prevents a higher score.

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 description covers local execution, the relationship to batch_import_folder, both parameters, a detailed return manifest example, and a KB reference. The main gap is the invalid example path, which creates a correctness issue, but overall the description is sufficiently complete for an agent to call the tool correctly in most cases.

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 Args section adds strong meaning beyond the 0%-coverage schema: folder_path is defined as an absolute local path with OS examples, and recursive is explained with its default. However, the bottom example uses '/Game/MCP_Test/Example', a UE content path, which directly contradicts the required local absolute path and could mislead an agent into passing an invalid argument.

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 opens with a specific verb and resource: 'Scan a local folder for importable assets' and states the output is a 'categorised manifest.' It further differentiates from siblings by explicitly noting it runs locally and does NOT connect to UE5, mentioning batch_import_folder as the related follow-up.

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 explicitly says 'Use it to preview what would be imported before calling batch_import_folder,' providing a clear when-to-use and naming the alternative. It also clarifies the local-only, non-UE5 context, so an agent will not try to use it for engine-side operations.

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