zins_get_cyber_incidents_by_threat_and_app

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

Annotations (readOnlyHint: true) already establish read-only safety. The description adds valuable behavioral detail: grouping by THREAT_CATEGORY_ID × APP_ID, nested `entries` structure, and the mandatory 7- or 14-day historical window. This goes beyond annotation defaults and helps set expectations for response shape and time-window constraints.

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 three concise sentences. It front-loads the purpose, then adds grouping details and the window constraint. No filler words, no repetition of schema content. Every sentence earns its place.

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 analytics tool with no output schema, the description covers purpose, grouping shape, use case, and a key time-window constraint. It doesn't mention default values for days_ago or explicitly describe the output record fields beyond `entries`, but it's reasonably complete for its complexity. A slightly longer note about adjusting the time window or default behavior would push it higher.

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 description coverage is only 17% (only `query` is described in the schema). The tool description does not explain `limit`, `start_time`/`end_time`, or `start_days_ago`/`end_days_ago`. The '7- or 14-day historical interval' constraint is mentioned, but not mapped to specific parameters, nor does it clarify the default window or how to select a 7-day window. The rich `query` documentation lives in the schema, not the description, so the description itself does not compensate for the coverage gap.

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?

Purpose is crystal clear: 'Get cyber-security incidents correlated by threat category and application' – a specific verb and resource with a defined grouping. This distinguishes it from sibling tools like zins_get_cyber_incidents_by_location, and 'Read-only analytics' explicitly confirms it's a non-mutating operation.

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 description gives a clear use case: 'useful for finding the most-targeted apps' via the per-application breakdown under nested `entries`. It implies this tool should be used when you need threat-category × application grouping, but doesn't explicitly name alternatives or mention when not to use it. Still, the context is sufficient for most selection scenarios.

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