get_integration_health

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

Annotations already declare readOnly/openWorld/idempotent, and the description adds genuinely non-obvious behavior: it explicitly detects zero-run stalls and 503/429 upstream failures, and enumerates the returned signals (counts, last success/failure timestamps, run details, alerts). It does not discuss permission requirements or how the 'recent window' interacts with the days parameter, leaving a small gap.

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?

Three dense sentences with no filler: purpose first, the differentiating silent-stall capability second, the return payload last. Every clause carries information the agent cannot get from 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?

With no output schema, the description compensates by enumerating the returned fields and alerts, and it explains the failure modes it catches. An agent can decide whether to call it and interpret the result without further information.

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?

Schema coverage is 100% and already documents defaults and the 365-day cap, so the baseline is 3. The description adds value by framing the window semantically ('over a recent window') and by naming NVD/Qualys feeds, which concretely illustrates what the source filter selects.

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?

States a specific verb and resource ('Report the health of Vulnerability Response data integration runs') and pins the underlying table (sn_vul_integration_run), so the agent knows it is an aggregate health view rather than a raw run listing. It stops short of naming the ambiguous siblings (list_integration_runs, get_integration_run, list_integration_logs), so the differentiation is inferred rather than explicit.

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?

Clear usage context: it is a recent-window health snapshot whose distinguishing value is catching silent stalls where no runs occurred. That implicitly selects it over raw run-listing tools, but no when-not condition or named alternative (e.g. list_integration_runs for raw history) is offered.

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