zdx_list_alerts

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

Read-only behavior is confirmed (matching annotation). The description adds the return fields and filter constraints, but does not disclose pagination (offset), rate limits, or behavior for empty results. With annotations covering read-only, the description adds moderate value.

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 sentences, front-loaded with the main purpose, no redundant words. Efficiently covers key 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?

Covers main functionality, return structure, and filter options. Missing pagination details (offset) and the query parameter, but for a list tool with good annotations, this is acceptable.

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 only 14% (only query documented). The description adds meaning to 4 of 7 parameters (location_id, department_id, geo_id, since), but does not explain limit, offset, or query beyond the schema. Partially compensates for low schema coverage.

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 clearly states the tool lists ongoing ZDX alerts, specifies the return structure (one triage row per alert with fields like id, rule, severity, etc.). It distinguishes from siblings by directing use of returned IDs with zdx_get_alert or zdx_list_alert_affected_devices.

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?

Provides filter options (location/department/geo, since with max 336h) and explains how to use the results. Lacks explicit when-not-to-use, but the scope 'ongoing' implies exclusion of historical alerts, and a sibling zdx_list_historical_alerts exists.

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