pve_diagnose

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

No annotations are provided, so the description must fully convey behavioral traits. It states 'No state change and no side effects' and 'READ-ONLY', which is good. However, it does not mention potential error conditions (e.g., unreachable node) or authorization requirements. The return type is mentioned as a dict, but details are left to the output schema.

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 extremely concise: a single purpose statement, safety declaration, usage alternatives, and default behavior—all in three well-structured sentences. Every sentence adds value without redundancy.

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?

Given the presence of an output schema and full schema coverage, the description covers the essential aspects: purpose, read-only nature, scope (node health), alternatives, and default parameter behavior. It could be slightly more complete by mentioning error scenarios or prerequisites, but overall it provides sufficient context for an agent to invoke the tool correctly.

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%, providing baseline value. The description reinforces the default behavior for the 'node' parameter ('omit to use the configured default') but does not add significant semantic detail beyond the schema for either parameter. The proximo_target parameter is not mentioned in the description.

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 starts with 'READ-ONLY:' and specifies the verb 'gather' with a clear resource ('one node's health evidence'). It lists the specific categories (node status, storage usage, recent failed tasks, advisory flags) and explicitly distinguishes from sibling tools pve_doctor and ct_diagnose.

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 says 'for triage' and gives explicit alternatives: use pve_doctor for token verification and ct_diagnose for container-level diagnosis. It also notes the default behavior for the node parameter. However, it does not explicitly state when not to use or list prerequisites.

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