engine_health_rca

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

With no annotations, the description carries the behavioral burden. It discloses what it reads (health check, version, clock, counts, specific event types), how it reports (rank order, quoting signal), and that it is a read operation (prefixed with [READ]). It doesn't mention side effects, permissions, or error conditions, but for a read-only diagnostic these are minor omissions given the detail provided.

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 well-structured: a crisp purpose line, a detailed but scoped explanation of what it reads, a usage directive, then parameter details. Every sentence adds value, and the key purpose is front-loaded. It is long but not padded; the structure aids parsing.

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 having no output schema, the description explains what the tool returns (findings in rank order with signal quotes) and why it's needed (unique alerts). All parameters are covered, and the usage priority is stated. For a complex RCA tool, this is complete enough for an agent to invoke 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 0%, so the description must compensate, and it does thoroughly. Each parameter is explained with purpose, range, and default: events_limit for 'correlation', events_window_hours for 'ignore events older', and target for choosing from config. This far exceeds the schema's bare type/default info.

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 and resource: 'Problems with the engine itself' and 'Reads the engine's health check...' It clearly distinguishes from siblings like host_health_rca and vm_health_rca by focusing on engine-specific alerts that 'appear in no other diagnosis.' The scope is unambiguous and the tool's unique role is stated.

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?

It gives explicit when-to-use guidance: 'call this first for "is anything wrong"' and explains that its alerts are exclusive ('appear in no other diagnosis'). This sets priority and differentiates from other RCA tools, even though it doesn't name them directly. The instruction to report in rank order also guides invocation.

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