incident_timeline

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds crucial context: 'read-only, stateless, no network — nothing is executed.' It also discloses the error behavior for malformed events, returning '{error, hint}' with the offending index, which goes beyond the annotation set.

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 organized into labeled sections (WHEN, INPUT, RETURNS, GOTCHAS) that allow quick scanning. Every sentence adds substantive value—no filler or redundancy—while front-loading the core purpose. The length is justified by the tool's complexity and the need to cover invocation context.

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 tool with no output schema, the description fully specifies the return object structure (event_count, window, spikes, hypotheses, next_checks) and mentions nested elements like suggested_check. It covers all four parameters, usage prerequisites, and error handling, making it complete for an agent to decide when to use it and how to invoke it correctly.

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 0%, so the description carries full responsibility for explaining parameters. It specifies the 'events' envelope fields, ts formats (ISO-8601, epoch seconds/millis), normalized severity, and explains all optional parameters (bin_seconds, z_threshold, top_n) with defaults and behavior. This far exceeds the bare schema and fully compensates for the lack of schema descriptions.

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 opens with 'Correlate already-fetched VMware events into one incident view,' which clearly states the verb (correlate), resource (already-fetched VMware events), and outcome (one incident view). It distinguishes itself from the sibling 'list_symptom_categories' by explicitly stating it does not fetch anything itself.

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 WHEN section gives explicit use-after-fetch guidance, names the data-source skills that produce the required input, and directs users to 'list_symptom_categories' when unsure which events to pull. It also states what the tool does NOT do ('does NOT fetch anything itself') and mentions remediation routing to vmware-aiops/vmware-pilot, covering both preconditions and follow-ups.

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