delete_cache_files

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

Beyond the destructiveHint=true annotation, the description discloses three traits annotations cannot express: missing files are reported per file (partial success semantics), deletion is only queued for the scheduler, and the tool cannot confirm the operation ran. That async fire-and-forget caveat is exactly the kind of behavior 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?

Three compact sentences, front-loaded with the action, then key format, then recovery route, then the async caveat. Nothing is wasted, though the telegraphic 'service omitted for global' phrasing reads as clipped rather than polished.

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, asynchronous, single-parameter tool with no output schema, the description covers the input key shape, how to discover valid keys, per-file failure reporting, recovery via run_jobs, and the inability to confirm execution. No material gap remains for an agent deciding to call it.

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 coverage is 100% and every field is already described in the schema, including 'omit for global' on service. The description restates the key fields and the global-service rule but adds no new syntax or format meaning, so baseline 3 applies.

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 opens with a specific verb+resource ('Delete job cache files') and immediately characterizes the input shape, so an agent can distinguish it from read-side siblings like list_cache_files or get_cache_file without opening the schema.

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 explicitly routes the agent to list_cache_files to obtain valid keys and notes run_jobs regenerates deleted files, which implies when deletion is safe. It stops short of stating exclusions or when deletion should be avoided entirely, so not a full 5.

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