fleet_incidents

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description adds 'Read-only; no device I/O' and a [risk=low] tag, clarifying that this tool does not interact with devices. This is useful behavioral context that goes beyond the structured hints, though it omits details like rate limits or auth requirements.

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 well-structured with a front-loaded summary line, labeled Args/Returns sections, and an example. It is somewhat verbose, repeating the read-only nature already in annotations, but each part serves a purpose and the format is easy to scan.

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 description thoroughly explains the single input parameter and the return dict structure, which is critical given there is no output schema. It also clarifies the fleet-wide aggregation scope. However, it does not cover edge cases (e.g., empty sites list, missing causes) or aggregation semantics (e.g., how top_causes are ranked), leaving a small gap.

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 input schema for 'sites' is a bare array of objects with no property descriptions (0% schema description coverage). The description fully compensates by detailing the expected structure: 'Per-site reports carrying incidents: [{site, incidents:[{cause|primary_cause, confidence?}]}],' and provides an exact example. This is essential for correct invocation.

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's function: 'Roll up active RCA incidents across sites → fleet-wide top causes.' It specifies the verb ('roll up'), the resource ('active RCA incidents'), and the scope ('fleet-wide'), distinguishing it from site-level tools like downtime_root_cause and aligning with the sibling set's fleet-analytics theme.

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 gives clear context: it aggregates per-site incident reports into a fleet picture, implying use when a fleet-wide root-cause overview is needed. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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