Find documents that use a path

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing the safety profile. The description adds valuable behavioral context: the exact path matching rule (folder matches files under it, never a longer name), the scan scope (every field of every world document), and the compendium exclusion. It does not describe output format or edge cases, but this is not required given the strong annotation coverage.

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?

Three sentences with no filler: action, path rule, usage context, and limitation each earn their place. The core function is front-loaded and the supporting rules are presented in a logical order.

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 read-only search tool with a simple parameter set and strong annotations, this description is complete: it states what is scanned, how path matching works, when to use it, and a key exclusion. The only minor omission is output format details, but no output schema exists and the tool's purpose makes the return type obvious.

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 100%, so the schema already documents all three parameters. The description goes beyond the schema by explaining the semantic behavior of the path parameter ('a folder matches the files under it, never a longer name'), which is essential for correctly interpreting what results will be returned. The maxResults and collections parameters are sufficiently documented in the schema.

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 states a precise verb-and-resource pair: 'Find every field of every world document that points to a file or folder path.' It also clarifies the exact matching rule and scope ('Compendiums are not scanned'), which makes it clearly distinguishable from file-related siblings like find-missing-files or world-rewrite-paths even without naming them. The title and description agree and add specificity.

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 an explicit usage scenario: 'Use it before moving or replacing files.' It also exposes a limitation ('Compendiums are not scanned') that tells the agent when this tool is insufficient. It does not explicitly name alternative tools or give detailed when-not-to-use guidance, so it stops just short of full routing guidance.

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