correlate_alerts

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description only needed to add behavioral context. It does so by disclosing that the tool groups alerts into clusters using device, datasource, and temporal proximity—key behavior an agent cannot infer from annotations alone. It does not mention output shape or algorithmic caveats, but the core analytic behavior is transparent.

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 sentences with no extraneous content. The action and grouping criteria are front-loaded in the first sentence, and the purpose is stated clearly in the second. It is appropriately sized for the tool's simplicity.

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 should clarify what a returned 'cluster' looks like, but it does not specify the response structure (e.g., cluster IDs, nested alert lists, ordering). However, the parameters are fully documented and the annotations confirm safety and idempotency, covering much of the operational context. The tool is adequately usable, but the missing output details are a clear 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?

Schema coverage is 100%, so the baseline is 3—each parameter (limit, device, group_id, severity, hours_back) already has a complete description with defaults. The description adds a mapping to two concepts (device and temporal proximity) but also mentions 'datasource,' which has no corresponding parameter in the schema; this is a minor ambiguity. Overall the description neither significantly enhances nor undermines the schema's parameter documentation.

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 states a specific verb ('correlate'), a clear resource ('alerts'), and the grouping dimensions (device, datasource, temporal proximity). It clearly distinguishes the tool from raw retrieval siblings like get_alerts and from more specific analysis tools like detect_alert_burst. The second sentence reinforces the purpose by naming the output concept (clusters to identify related issues).

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 implies when to use it—when you want alerts grouped into related clusters rather than a flat list—but it does not explicitly name alternatives or state when not to use it. Given the large sibling set including get_alerts, get_alert_details, and detect_alert_burst, explicit routing guidance would have been valuable. The intended use case is reasonably inferable but not directly stated.

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