pve_ceph_cmd_safety

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

With no annotations provided, the description carries the full burden and excels: it explicitly labels the tool as READ-ONLY and ADVISORY ONLY, details behavior when Ceph is unreachable (never fabricates safe=true), and describes the expected output shape with safe and optional status fields.

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 yet comprehensive, front-loading the critical purpose and caveats in the first sentence. Every sentence adds value: purpose, advisory nature, behavior under failure, and output shape. No wasted words.

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?

Despite lacking annotations, the description covers purpose, behavioral transparency, output details, and usage guidance. The 5 parameters are fully described in the schema, and the output is hinted. It is sufficiently complete for the agent to understand when and how to use the tool.

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 100%, so the baseline is 3. The description references the endpoint URL with parameter placeholders but does not add new semantics beyond what the schema already provides for each parameter.

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 explicitly states it is a read-only heuristic advisory for whether it is safe to stop or destroy a Ceph instance, clearly identifying the verb (check advisory), resource (Ceph mon/mds/osd safety), and distinguishing from sibling tools that perform the actual stop/destroy operations.

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 clearly states that the tool is advisory only and never a gate, explaining that the plan must still render even if Ceph is unreachable, producing a 'cmd-safety unavailable' note. It implies its usage as a pre-check before destructive actions, though it does not explicitly name alternative tools.

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