project_find_assets

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

With no annotations provided, the description carries the full disclosure burden and exceeds it. It reveals pagination behavior (page/limit for large sets, max 1000, 0-based page), tag filter semantics (AND combination, empty = no filter), empty class_names behavior (all classes), the recursive default, and the exact shape of returned asset descriptors with examples. This is rich behavioral context far beyond the name and schema.

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 longer than average but every section earns its place given the 0% schema coverage: purpose, pagination note, return format, per-parameter semantics, returns line, KB pointer, and a working default example. It is front-loaded with the core purpose and uses compact formatting (labels, examples, defaults) rather than prose padding.

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 6-parameter tool with no annotations and no schema descriptions, this description is complete: it documents all parameters, return value shape, pagination, defaults, and edge-case behavior, plus a KB reference and example. The output schema exists and is referenced ('outputs.assets list'), so return-value coverage is handled without redundancy. Nothing an agent needs to call this correctly is missing.

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 fully compensate — and it does. Every one of the 6 parameters gets semantic meaning beyond the bare schema: class_names gets an example and empty-value behavior, package_paths gets an example root path, tags gets AND semantics, limit gets its max, page gets its 0-based indexing. Nothing is left to inference.

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: 'Find assets in the Unreal project using the Asset Registry.' It then names the search dimensions (asset class, package path, tag filters), which distinguishes it from the near-sibling ue_find_assets_by_class (class-only) and scan_project_assets (scanning vs targeted find). An agent can tell what this tool does and how it differs without opening either schema.

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 gives clear context for when the tool is appropriate — searching by class, package path, and tags, with pagination for large sets — so usage is implied but never stated explicitly. It does not name any alternative tool, unlike the ideal pattern of 'use X instead of Y when...', and given the existence of ue_find_assets_by_class as a very close sibling, explicit exclusion guidance would be valuable. The KB pointer is indirect and does not cover this gap.

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