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

Annotations already mark it read-only, idempotent, safe, but the description adds substantial behavioral context: live WMI read, 60s server timeout, 400 response for offline/unenrolled devices, and the wrapped API endpoint with permission scope. No contradiction with annotations.

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 purpose is front-loaded in the first sentence, and each subsequent sentence adds distinct value (endpoint, permission, use case, constraints, latency, errors, example). No filler or restating of the tool name.

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 one-parameter read-only endpoint with rich annotationsaced and no output schema, the description covers success shape, expected fields, failure modes, latency expectation, and a concrete call example. Nothing needed to invoke it 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 100% (device_id described in schema) so the baseline applies. The description adds only modest semantic value: it frames device_id as the agent-managed host to query and gives an example call. No enum or conditional behavior to clarify.

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+resource ('List Windows services on an agent-managed device'), a live-read semantics statement, and the wrapped endpoint. It is unambiguous and clearly distinct from siblings like agent_processes or agent_disk_usage.

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?

'Use this to answer is service X running on host Y' gives an explicit when-to-use. 'Service-control endpoints are deliberately NOT exposed' gives a clear when-not-to-use, preventing calls to a tool that can't start/stop services.

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