health_check

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

Annotations already declare readOnly, openWorld=false, idempotent, non-destructive; the description adds genuinely new behavioral facts: no network calls to Google, no browser launch, and specifically that ADC is not probed. That is exactly the kind of detail an agent needs to know this is a safe, purely local inspection. It stops short of saying what the check actually inspects or reports.

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?

Two tight sentences with the negative scope front-loaded and no filler. Every clause carries information an agent cannot get from the schema or annotations.

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 no explanation, and annotations carry the safety profile. However, for a diagnostic tool the description never says what is being examined or how to interpret a pass/fail result, and the undocumented `account` parameter leaves a real gap.

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 single `account` parameter has 0% schema description coverage and the description never mentions it — no indication whether it selects which stored credential's configuration to inspect or what happens when it is omitted (the schema shows default null). With zero coverage, the description was the only place this could have been clarified.

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?

"Check local configuration" states a verb and a resource, but the resource is vague — it never says this is BigQuery configuration (only the annotation title does), nor what aspect of configuration is verified. The negative scope ("without contacting Google or opening a browser") is helpful but describes what the tool avoids rather than what it produces, and no sibling tool is referenced for contrast.

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?

There is no statement of when to run this check — before a query, when auth fails, as a preflight — and no comparison to any of the nine sibling tools. The only guidance is an exclusion: "ADC is not probed," which tells an agent not to rely on it for auth diagnostics but does not say what to do instead.

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