Repeat late arrivals

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that the tool ranks employees and returns metrics, which is some behavioral context. However, it does not disclose output format, sorting order, or any side effects (though none expected). Given the annotations, the description adds modest value but not rich detail.

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 two sentences, front-loaded with the core purpose and output metrics, followed by a concise usage hint. No wasted words; it is efficient and well-structured for quick comprehension.

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?

The tool has 6 parameters, no output schema, and moderate complexity. The description covers the purpose and output metrics but omits details about the 'min_times_late' threshold (which defines 'repeatedly') and the 'limit' parameter. It also does not describe the response format. These gaps mean an agent may not fully understand how to configure the call or interpret results without additional inference.

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 67% (4 of 6 parameters have descriptions). The descriptions for 'to', 'from', 'location', and 'grace_minutes' are provided in the schema, but 'limit' and 'min_times_late' lack descriptions. The tool description does not clarify these parameters, nor does it explain how 'min_times_late' relates to 'repeatedly'. The description adds no parameter semantics beyond the schema, so it fails to compensate for the undocumented fields.

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 ranks employees who were late repeatedly, and specifies the metrics (late count, late rate, average minutes late). It also includes a usage phrase ('who is regularly late') that helps distinguish it from siblings like find_late_arrivals. This is a specific verb+resource+output combination.

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 includes an explicit usage context: "Use for 'who is regularly late' questions." This gives clear when-to-use guidance. However, it does not mention alternatives or exclusions, even though siblings like repeat_missing_clock_events exist. The guidance is sufficient for the primary scenario but lacks explicit comparison.

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