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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them by disclosing the counting precedence ('disabled overrides paused, then maintenance, then up/down/unknown') and the full status priority ladder, which an agent cannot infer otherwise. It stops short of describing the response shape or what causes 'no services' to be a real state.

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 aggregation rule is front-loaded and every clause carries specification content rather than filler. The status ladder is a long semicolon chain that is dense but justified, and the trailing 'otherwise disabled' is slightly awkward phrasing rather than waste.

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 no-parameter, no-output-schema aggregation tool spanning three resource types, the description supplies counting and status semantics but never characterizes the returned payload (fields, counts object shape, incident summary contents). The dangling AsOfUtc reference further leaves an ambiguity an agent must resolve by guessing.

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?

With zero parameters the baseline would be 4, but the description references an 'AsOfUtc' time anchor that does not exist anywhere in the input schema, which risks an agent trying to pass a timestamp. The cross-reference to IncidentSummary's window semantics is useful but undefined in place.

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 opens with a specific verb ('Aggregate') plus explicit resources ('non-deleted monitors, heartbeats, and incidents') and scope ('in the authenticated organization'), which cleanly separates it from the per-resource siblings like monitor_list, heartbeat_list, and incident_list. An agent can tell this is the org-wide rollup without inspecting any schema.

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?

Usage is implied by the aggregate framing but never stated: there is no explicit 'use this when you need a single health verdict instead of per-resource lists' routing, and no mention of when to prefer incident_summary or the individual list tools. It also gives no prerequisites or conditions for calling it.

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