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

No annotations are provided, so the description carries the full behavioral burden. It doesn't state that the call is read-only, whether results are aggregated over a time window, what metrics are included, or anything about cost/latency for a fleet-wide scan.

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 single front-loaded sentence with zero filler; the scope qualifier is placed immediately after the core purpose. Nothing is repeated or wasted.

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 and no annotations, the description should at least sketch what 'statistics' means (counts, per-agent breakdown, time window). As written, an agent knows the scope but not what it will receive back.

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?

The tool takes zero parameters, so there is nothing for the description to clarify; baseline 4 applies. The description adds the meaningful scoping note that results cover only the caller's own agents.

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?

States the resource (duty statistics) and the scope (whole fleet, restricted to the caller's own agents), which distinguishes it from the per-agent siblings like duty_state and duty_check. It lacks an explicit verb such as 'get' or 'retrieve', 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 parenthetical 'your agents only' implies a fleet-wide overview versus per-agent calls, but the description never says when to use this instead of duty_state or duty_check, nor any preconditions. Usage must be inferred entirely from the sibling names.

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