cluster_health

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

Without annotations, the description must disclose behavioral traits. It marks the operation as [READ] and describes the output format (plain-language cause + action). However, it does not mention permissions, rate limits, potential latency, or error handling. The disclosure is adequate but not exhaustive.

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 and front-loaded with the purpose. The first two sentences convey the core functionality and usage guidance. The parameter description is brief but sufficient. No unnecessary fluff; the example codes add clarity without excessive verbosity.

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 no output schema, the description hints at the return format (cause + action per check) but does not detail the exact structure, error handling, or whether raw status is also included. For a tool with one optional parameter, it is mostly complete but leaves some gaps about the output.

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?

The input schema has 0% description coverage for the 'target' parameter. The description adds meaning by stating it is a Ceph target name from config and can be omitted for the default. This adds value beyond the schema, but could be more specific about the default value or format. It compensates for the schema gap partially.

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 reads health status and provides plain-language cause and action per active check. It specifically says it decodes raw HEALTH_WARN/ERR codes, distinguishing it from siblings like cluster_status which may provide raw status. The verb 'read' and resource 'health status' are specific.

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 explicitly recommends calling this tool first for cluster health questions and explains it decodes raw codes. It does not list alternatives or when not to use, but the guidance is clear enough for the primary use case. Sibling tools like osd_df or pool_df are for specific sub-components, so the context is sufficient.

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