get_broken_script_refs

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

No annotations are supplied, so the description carries the full disclosure burden. It states the scan scope (prefabs/scenes) but says nothing about whether the scan is read-only, how expensive it is on a large project, whether results are deduplicated, or what a returned entry looks like. 'List' implies a read, but the rest of the behavioral profile is left to inference.

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?

A single sentence that front-loads the verb and the target, with the parenthetical gloss giving the plain-language name of the condition. Nothing is wasted and nothing is buried.

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 zero-param tool there is no schema complexity to explain, but there is also no output schema, so the description is the only source of information about results. It tells the agent what qualifies as a hit but not what fields or shape the returned prefab/scene entries have, leaving a gap an agent must discover by calling.

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 tool takes zero parameters, which is the baseline-4 case; there is no parameter meaning to add or omit. The description correctly reflects a no-argument listing operation without inventing filter options.

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?

Uses a specific verb (List) plus a precisely scoped resource: prefabs/scenes referencing a script GUID that has no .cs file in the project. The parenthetical 'missing script refs' names the concept, and the scope distinction (script refs, not asset refs) is inherently separable from siblings like get_broken_asset_refs. It stops short of explicitly naming an alternative, which is what keeps it at 4 rather than 5.

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?

Usage is implied by the diagnostic framing: an agent would call this when hunting for missing script references. There is no explicit 'use this instead of X' guidance or statement of when not to use it, which matters given siblings such as get_broken_asset_refs and find_script_references sit nearby.

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