springboot_diagnose_health

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: results are pre-sanitized, component drill-down happens locally, and log/heap-dump/raw-stack retrieval is deliberately out of scope — useful expectations for an agent interpreting the payload.

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?

A single dense sentence with the return payload front-loaded, then the trigger condition, then the scope exclusions — no filler. The semicolon-separated structure is readable, though the parameter surface is compressed away entirely.

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?

An output schema exists, so return values need not be re-explained, and purpose/trigger/boundaries are well covered. But for a tool exposing eight optional parameters — including a pagination cursor, a target selector, and detail/healthy toggles — with zero schema descriptions, the description leaves an agent unable to choose parameters intelligently.

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?

Eight parameters with 0% schema description coverage means the description carries the full explanatory burden, and it largely abdicates it. Only componentPath gets an indirect nod ("组件下钻在本地完成"); group, targetId, maxDepth, maxResults, cursor, includeDetails, and includeHealthy are left entirely undefined in both schema and prose.

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 names specific outputs (overall health status, an abnormal-component tree, sanitized structured errors plus remediation code), which is a concrete verb+resource pair rather than a restatement of the name. It is clearly separable from the inspection/mapping siblings, though it never names them explicitly.

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?

"依赖故障或探针异常时调用" gives an explicit triggering condition for use. The trailing clause functions as a negative boundary (no logs, heap dumps, or raw exception stacks), but no alternative tool is named for those needs, so it falls short of a full when-not/alternatives map.

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