device_facts

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is read-only, lists the returned fields, and mentions the interface name list. It does not mention side effects or permissions, but for a read tool this is sufficient. Slightly generic on whether all fields are always returned, but overall good.

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 description is concise: two short paragraphs, front-loaded with '[READ]' and key facts. Every sentence adds value, no wasted words.

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?

With no output schema, the description adequately explains return values (hostname, vendor, model, etc.) and mentions the interface name list. It also references a sibling tool for more detail. The single optional parameter is fully covered.

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?

The description adds meaning to the 'target' parameter beyond the schema: 'Device name from config; omit to use the default device.' This compensates for the 0% schema coverage, though it could also explain the format or constraints of the device name.

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 clearly states this is a READ operation for core device facts, listing specific fields (hostname, vendor, model, OS version, serial, uptime) and distinguishing from sibling 'get_interfaces' by noting it also returns interface names. The verb+resource is unambiguous.

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?

Explicitly tells when to use an alternative: 'Use get_interfaces for per-interface state/speed.' Also explains when to omit the target parameter. This provides clear usage context.

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