get_kpis

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

With no annotations, the description carries the full behavioral burden, but it only lightly implies a safe read via 'snapshot' and states the return wrapper 'KPI dict with status="ok"'. It says nothing about permissions, caching/refresh semantics, or whether the snapshot is real-time — gaps that matter for a monitoring tool.

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 metric list is front-loaded and the description is short. The 'Returns: KPI dict with status="ok"' line is largely redundant given an output schema exists, which is the one wasted fragment.

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 zero-parameter read tool with a full output schema and no annotations, the description is nearly sufficient: it tells the agent what metrics come back and that the call is a snapshot. The missing piece is when to prefer this aggregate over the sibling list/status tools.

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 the baseline is 4. There is nothing for the description to disambiguate, and the enumerated metric names usefully pre-announce the shape of the payload the agent will receive.

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 names a specific resource (network health KPIs) and enumerates the exact metrics returned (on_time_rate, in_transit, delayed, exceptions, delivered_today, low_stock_skus, fleet_utilization, open_pos, critical_active). This is far more concrete than a tautology, though it never contrasts itself with siblings like check_inventory or track_shipment, which also surface operational status.

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?

There is no explicit when-to-use guidance, no prerequisites, and no mention of alternatives. An agent must infer that this is the dashboard/aggregate call rather than one of the shipment- or inventory-specific siblings; the description does nothing to route that decision.

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