pve_guest_config

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

With no annotations, the description carries the full burden, and it does disclose that this is a mutating tool, that pending=true surfaces reboot-pending changes, and that digest provides optimistic-concurrency protection — genuinely useful beyond structured fields. It does not say what permissions/auth are required, that delete removes config entries (destructive), or what a read returns, so a mutation tool still has meaningful undisclosed behavior.

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 dense and front-loaded, leading with the read/write split before drilling into per-parameter behavior, and the inline JSON examples convey more than prose would. The telegraphed style ('pending=true shows changes waiting for a reboot') is efficient rather than sloppy.

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 dual-mode read/write tool with five undocumented parameters and no output schema, the description covers the mutation path and concurrency well but says nothing about what a read returns or how pending output is shaped. An agent can call it correctly, but cannot anticipate the read response at all.

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 0%, so the description must compensate, and it largely does: 'set' is given a concrete object example with memory and net1 keys, 'delete' is shown as a list of config keys to remove (ide2), pending is explained as showing reboot-pending changes, and digest is explained as a concurrency token taken from a prior read. Only vmid is left implicit, which is a minor gap given it is the required identifier.

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 pair: 'Read a guest's config, or change it', and immediately shows what a change looks like via the set/delete examples. It is clear this is the config read/write tool rather than a lifecycle tool like pve_create_guest or a status tool, though it never explicitly distinguishes itself from the sibling pve_guest, which may also read guest data.

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?

Usage is only implied by the examples: pass set/delete to mutate, pending=true to inspect pending changes, digest to guard against concurrent edits. There is no explicit 'use this instead of X when Y' routing, no statement about when a read-only call is preferable, and no prerequisite (e.g. guest must be stopped for some changes) spelled out.

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