datto_edr_scan_host

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, but the description adds real value beyond them: the HEADLINE high-impact warning, the fact that it consumes endpoint resources, the dry-run/confirm gating behavior, and the task-id return value. It doesn't cover permission requirements or whether a scan can be cancelled, which keeps it from a 5.

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 short clauses with the most decision-relevant warning ('⚠ HIGH-IMPACT') front-loaded, followed by the mechanism, the confirmation gate, and the handoff tool. No filler and nothing repeated from the schema verbatim beyond what's needed for emphasis.

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 destructive, non-idempotent, nested-parameter tool with no output schema, the description supplies the essentials: impact level, endpoint side effects, confirmation semantics, and the returned task id. It leaves out authorization prerequisites and whether repeated scans are safe or throttled, which would matter for a high-impact operation.

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%, so the schema already documents target, confirm, target_group_id, and even the options sub-flags with their defaults. The description only reinforces the confirm parameter and says nothing about how the options collection affects scan scope or runtime — baseline 3 is correct when the schema does the heavy lifting.

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 a specific verb and resource ('Start a forensic scan of one host') plus the underlying endpoint (POST /api/targets/scan). This cleanly distinguishes it from sibling read tools like datto_edr_scans_list and datto_edr_scans_get, which retrieve scan records rather than initiating one.

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?

Establishes context (one host, forensic scan) and an explicit gate: 'Requires confirm: true; without it, returns the request it would send.' It also names the follow-up tool (datto_edr_tasks_get) for polling results. It stops short of naming alternatives such as datto_edr_isolate_host or explaining when a scan is not warranted, so it doesn't reach 5.

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