scan_uasset_refs

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

Annotations already declare readOnly/idempotent/non-destructive/non-open-world. The description adds genuinely useful context beyond them: no editor load, raw byte tokenization, dual disk/mount path acceptance, and the stub-vs-complete comparison heuristic.

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?

Front-loaded with the core behavior and use case, followed by the returns block. The dense Returns enumerations are justified because no output schema exists, though they lengthen the definition considerably.

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 no output schema, the description compensates by enumerating the return fields (ref_paths, matches, file metadata). Combined with annotations covering the safety profile and full schema coverage of inputs, an agent has everything needed to call 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 100%, so the baseline is 3. The description restates that `pattern` is a regex matching tokens and that a disk or mount path is accepted, which is largely already in the schema descriptions, adding little new syntax or format detail.

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?

States a specific verb (scan) plus resource (.uasset/.umap) and the distinguishing method (lightweight BINARY, no editor load). It separates itself from sibling tools like get_asset_dependencies and audit_asset_references by emphasizing the raw on-disk byte-level tokenization.

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?

Provides a clear use case: 'a quick way to compare copies of one asset' where a stub copy shows fewer tokens. It implies when this beats a full editor load but does not explicitly name alternatives or exclusion conditions versus sibling reference tools.

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