observability_overview

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

With no annotations, the description carries the transparency burden. The leading `[READ]` tag communicates read-only behavior, and the summary of included counts indicates what to expect. Yet it does not disclose potential partial-failure behavior, caching, or requirements beyond the target from config, leaving some behavioral gaps.

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 compact and front-loaded: a one-sentence summary, a bullet-like breakdown of included metrics, and a short Args note. Every sentence adds information without padding or 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?

For a read-only snapshot tool with one optional parameter and no output schema, the description covers the purpose, main return contents, and parameter semantics. It is sufficient for an agent to select and invoke the tool, though it could mention behavior when a platform is unreachable.

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 schema provides only a `target` parameter with no description (0% coverage). The description compensates by explaining it is 'Target name from config; omit for the default,' giving semantic meaning to the parameter's usage and default behavior, which is essential since the schema offers no help.

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 '[READ] Platform-aware health snapshot for the target,' providing a clear action (snapshot) and resource (target's platform health). It then enumerates specific metrics (Prometheus alert count, scrape up/down, rules erroring; Grafana counts), distinguishing it from more granular sibling tools like `firing_alerts` or `list_dashboards`.

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 phrase 'health snapshot' implies a high-level overview use-case, which clearly contextualizes when to use it relative to more detailed sibling tools. However, it does not explicitly name alternatives or state when not to use it, so it stops short of the full guidance level.

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