latest_detections

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered; the description adds genuinely new behavior — a v2→v1 fallback, window pagination, and local sorting. It does not explain how severity_min interacts with limit (filter-before-or-after-top-N) or what fields the detection records carry, which matters given there is no output schema.

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?

Four sentences, each carrying distinct information: what it returns and its ordering, which tool to pick instead, why the alternatives fail, and what the composite does internally. The most decision-relevant facts (ordering and the tool-vs-tool choice) are front-loaded with no filler.

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-required-parameter read tool with no output schema, the description covers the ordering guarantee, window behavior, fallback and the routing decision, which is most of what an agent needs. The remaining gap is the shape of the returned detections, since there is no output schema to fall back on.

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 100%, with defaults, bounds and the severity enum all documented in the schema itself, so the baseline is 3. The description adds only the implicit context that the time window is paginated and results are capped by limit; it adds nothing about hours bounds or severity_min semantics beyond what the schema states.

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 states a specific resource and scope — 'Newest detections in a time window, sorted by occurTime descending' — which tells an agent both what is returned and how it is ordered. It explicitly distinguishes itself from the raw list endpoints in the sibling set (incident_detections__list_detections_v1/v2), so disambiguation needs no schema inspection.

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?

It gives explicit when-to-use guidance with a concrete user intent ('what's the latest detection / what happened recently') and an explicit when-NOT-to-use: the raw list_detections_* endpoints, with the reason spelled out (they don't sort by date, so first-page results are stale). Alternatives and exclusion condition are both named.

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