pve_acl_prune

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

With no annotations provided, the description carries the burden. It discloses it is a mutation, synchronous, dry-run by default, and shows a plan with principals and shadow/widen gotchas. It does not detail auth needs, rate limits, or the exact destructive effects of execution.

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 concise (two sentences plus a roleid note) and front-loaded with 'MUTATION'. It is efficient but could be more structured with separate lines for dry-run vs execution.

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 assumes knowledge of pve_overbroad_grants and the plan output. It does not explain the return value or behavior when confirm=True without narrow parameters. Given the output schema is not shown, it provides adequate but not full context.

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 low (13%), yet the description only explains roleid ('the over-broad role to remove'). Other parameters like path, target, confirm, narrow_path, narrow_role are not described, leaving significant gaps for the agent.

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 clearly states the tool prunes an over-broad ACL grant flagged by pve_overbroad_grants. It specifies the verb 'prune' and resource 'ACL grant', distinguishing it from siblings like pve_acl_modify (general modification) and pve_overbroad_grants (detection).

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 explains the dry-run default and the need to re-call with confirm=True to execute, providing a clear workflow. It implies usage after pve_overbroad_grants but does not explicitly mention alternatives like pve_acl_modify or conditions when not to use.

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