run_script

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

Goes well beyond the destructiveHint=true/readOnlyHint=false annotations: it discloses SYSTEM privilege, synchronous wait semantics, stdout truncation at ~10,000 chars, 'never reboots', and that offline endpoints remain pending. These are exactly the operational traits an agent needs before firing a remote script.

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 tight sentences, front-loaded with the action and privilege context, with no filler. Each clause (return format, no reboot, offline handling) carries distinct operational value.

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 synchronous mutation with no output schema, the description covers privilege level, return shape (status + capped stdout), reboot behavior, and the async/offline path. Nothing an agent needs to call it safely and correctly is missing.

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 coverage is 0%, so the description must carry the load. It clarifies wait_seconds ('wait up to wait_seconds') and endpoint_ids provenance (ids from list_endpoints) and implies script is PowerShell, but org_id is entirely unexplained and no formats/defaults are given, so the low-coverage schema is only partially compensated.

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 (Run), resource (PowerShell script), execution target (given endpoints) and privilege context (as SYSTEM, now = synchronous). This clearly separates it from siblings like deploy_updates (patch deployment) and the list_* read tools.

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?

Gives concrete routing: endpoint ids come from list_endpoints, and offline endpoints 'stay pending - check later with list_automation_instance_endpoint_results(instance_id)'. This is real alternative/context guidance, though it never explicitly states when to prefer this over a scheduled automation or deploy_updates.

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