Prune expired files from the sync store

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

With no annotations, the description carries the safety burden. It usefully discloses what is destroyed (rows and their bytes) and what is protected (only files past retention horizon), but omits permissions required, reversibility, idempotency, and rate limits for a destructive operation.

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 front-loaded sentence that names the action, the target, and the scope constraint with no filler. Every clause earns its place.

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 destructive, annotation-free, zero-parameter tool the description does reasonably well by bounding scope, but it lacks confirmation/irreversibility warnings and any hint of what the call returns or whether it is safe to repeat.

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, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies the operation is parameterless and account-scoped rather than inviting spurious inputs.

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 (delete/prune) and resource (this account's files, rows and their bytes) with a clear scope qualifier (past their retention horizon). The destructive scope inherently distinguishes it from siblings like file_sync_list and file_sync_pull, though no sibling is named.

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 retention-horizon phrasing implies when to use it (cleaning up expired data), but there is no explicit when/when-not guidance, no mention of prerequisites such as authentication or an account context, and no statement of whether it runs automatically or on demand.

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