List Events

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

No annotations are provided, so the description carries the full burden, yet it discloses nothing about behavior: no ordering guarantees, no statement of what happens when results exceed max_results (truncation vs pagination), no note that the call is a read-only operation, and no permission or volume expectations. It only describes filter semantics, which belong to the parameter dimension. For a six-parameter query tool with zero annotation coverage this is a significant 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?

A one-line scope statement followed by a compact per-parameter list is front-loaded and wastes little. Every clause carries information, and the alternative-tool routing is placed at the end where the agent will read it alongside the only_alerts definition. Slightly terse in places ("Eventos do CM") and the mixed Portuguese/identifier prose is a minor readability cost.

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?

An output schema exists, so return values need not be explained, and the filter coverage is strong. What remains missing is proportionate to the tool's complexity: max_results behavior, result ordering, and whether a truncated result set is signalled. The mismatch between the stated severity default behavior and the schema default of CRITICAL is addressed, which is the most important completeness item here.

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 0%, so the description must compensate, and it largely does: it supplies the accepted severity values (CRITICAL, IMPORTANT, INFORMATIONAL, or None for all), the category values (HEALTH_EVENT, LOG_MESSAGE, AUDIT_EVENT, ACTIVITY_EVENT, SYSTEM), the meaning of service filtering, and the semantics of only_alerts. These enum-like lists are absent from the schema, where severity and category are untyped strings. The notable omission is max_results, which is never mentioned despite materially affecting the result set.

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 first line states the resource and scope: CM events within the last N hours, then enumerates the filter dimensions. The closing sentence distinguishes it from cluster_health_report, which aggregates alerts by severity and service, so an agent can tell the two apart without opening either schema. It lacks an explicit verb ("list") and uses the abbreviation "CM" without expansion, but the intent is unambiguous.

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 explicitly routes grouped-alert needs to cluster_health_report, giving a concrete alternative with a condition that selects it. It also defines the default severity scope ("None para todos"), which is critical since the schema default is CRITICAL and a null would otherwise be ambiguous. It gives no guidance on when not to use it or how it relates to list_audits or get_role_log, which overlap with the AUDIT_EVENT and LOG_MESSAGE categories.

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