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

The annotations declare destructiveHint and idempotentHint, and the description adds useful context beyond them: irreversible deletion, the exact set of things that survive (unexpired copies, upstream results, jobs, credit accounting, idempotency records), and the fact that repeated runs are safe and incur no new processing charge. This is exactly the blast-radius and side-effect information an agent needs before calling a destructive tool.

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?

It is front-loaded with the action and use case before the safety caveats and alternative routing, so scanning is easy. It is dense with clauses, though every clause carries real information; it could be split for readability but nothing is wasteful.

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?

There is no output schema, but the description names the return value (removed_expired_results), so the agent knows what to expect. Combined with the coverage of irreversibility, surviving data, idempotency, and billing effects, nothing an agent needs in order to call this correctly is missing.

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 0 parameters, which is the baseline of 4, and the description accurately says it takes no arguments. The schema's own description already states that an empty object is required and that company and permissions come from the authenticated connection, so the description adds nothing misleading and nothing missing.

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 begins with a concrete verb plus resource: delete expired local result copies and stale temporary download files, scoped to this company adapter's result directory. That is specific enough to distinguish it from sibling tools such as skavio_cancel_job, skavio_reconcile, or skavio_download_result.

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?

It names the triggering conditions ('local_storage_limit or routine artifact maintenance') and explicitly steers agents to skavio_cancel_job and skavio_reconcile for adjacent needs. Both the when and the when-not are covered with named alternatives.

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