ztna_health_sample

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

readOnlyHint=true already tells the agent this is a safe read, and the description does nothing to extend that beyond restating it as "[READ]". "Partial probe errors" vaguely hints that results may be incomplete or contain probe failures, but it does not say what that means, how to detect it, or whether an error field or truncation should be expected.

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?

It is a single short sentence with no wasted words, which is good. However, the trailing clause about "partial probe errors" is cryptic rather than informative, so brevity comes at the cost of clarity instead of being front-loaded useful information.

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?

There is no output schema, so the description carries the burden of explaining what a "sample" returns — for example whether it is one record per site/connector/application or a rolled-up health summary — and it does not. For an aggregate health tool with an unknown result shape, this leaves the agent guessing.

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 parameter "limit" has 0% schema description coverage, but its meaning and default (20) are self-evident from the name and schema default. The description adds nothing about how the limit affects the sampling or what happens when more sites/connectors/apps exist than the limit allows.

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?

"Sample site, connector and application health" gives a verb and the resources covered, so the general intent is graspable. But "with partial probe errors" is unexplained jargon, and the description never distinguishes this aggregate health check from the per-resource siblings ztna_site_status, ztna_application_status, and ztna_connector_metrics.

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?

No when-to-use guidance is offered, and no alternative is named even though the sibling list contains several status/metrics tools that overlap in purpose. The "[READ]" prefix signals a read operation, but that is already conveyed by readOnlyHint, so it does not function as real usage guidance.

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