list_files

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

With no annotations provided, the description carries full behavioral disclosure. It thoroughly explains each file state, the meaning of 'stale_scheme' relative to staleChunkCount, and edge cases such as 'unreadable' requiring optional extras and data/url sources not having disk state. This is highly transparent and provides actionable context beyond simple read/write hints.

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 front-loaded with a clear one-sentence purpose, then elaborates on the various file states in a structured manner. It is somewhat long, but every sentence contributes to explaining the behavioral nuances. The paragraph format works well for the complexity, though it could potentially be split into a bulleted list for readability.

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 is remarkably complete regarding behavioral semantics, covering all state types and their implications for syncing. The output schema exists, so return format is not needed. However, the omission of the 'scope' parameter is a notable gap, leaving the only input parameter unexplained. This prevents full completeness for an agent selecting and invoking the tool.

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 input schema defines a single optional 'scope' parameter with no description, and the tool description does not mention this parameter at all. With schema description coverage at 0%, the description must compensate, but it fails to do so. The agent is left without any guidance on what 'scope' means, how to format it, or what values are valid.

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 the tool 'lists files found on disk under the document roots, plus indexed data/url sources', using a specific verb and resource. It distinguishes itself from sibling tools like read_file and delete_file by focusing on listing files with their indexing states rather than manipulating content.

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 provides clear context on when to use the tool: to inspect file states and determine which files need syncing. It explicitly notes that states other than 'ingested' and 'unreadable' require a sync_start, giving actionable guidance. However, it does not explicitly name alternative tools or specify when not to use this tool.

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