ct_diagnose

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

Without annotations, the description fully conveys the tool's read-only nature ('READ-ONLY', 'No mutation, no confirm') and its conditional data completeness (full with exec, partial without). It describes the return value structure and the advisory flags. No contradictions; behavior is well disclosed.

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 (5 sentences) and front-loaded with 'READ-ONLY'. It efficiently covers purpose, permissions, behavior, and alternatives without fluff. A more structured format (e.g., bullets) could slightly improve readability, but it is already clear.

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 tool's medium complexity and the presence of an output schema, the description covers purpose, prerequisites, conditional behavior, and alternatives. It does not mention error handling or idempotency, but these are implied by the read-only nature. Overall, it is sufficiently complete.

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%, so the schema already documents all 4 parameters (ctid, kind, node, proximo_target). The description does not add any additional semantic detail beyond what is in the schema, resulting in a baseline score of 3.

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 is READ-ONLY and gathers 'what's broken' evidence for a container, including API status, in-container battery (failed units, disk, errors, memory, ports), and advisory flags. It distinguishes itself from sibling tools like ct_logs (same permission requirements) and pve_diagnose (node-level).

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 when to use this tool (for container diagnostics) and provides explicit alternative (pve_diagnose for node-level). It also notes prerequisites (PROXIMO_ENABLE_EXEC and CTID allowlist) and behavior when exec is off. However, it does not explicitly state when not to use it among siblings like ct_exec or ct_psql.

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