get_system_resource

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false), lowering the bar. The description adds useful interpretive context about what the numbers mean and the sniffer-saturation caveat, but discloses nothing behavioral about scope, target device resolution, or invocation cost.

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?

Front-loads the payload contents in one sentence, then a short block of operator guidance. The CPU-sniffer remark is arguably extra, but it is short and practically useful rather than 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?

An output schema exists, so return-value enumeration is not required, and the description still summarizes the returned fields. The only substantive gap is the undiscussed `device` parameter; everything else needed to call this read-only diagnostic is present.

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 0% for the single `device` parameter, and the description never mentions it at all, so the agent gets no explanation of what device identifies, what a null default resolves to, or whether omission targets a local/default device. With low coverage the description is expected to compensate and does not.

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+resource and enumerates exactly what is reported (uptime, RouterOS version, board name, architecture, CPU, memory), which distinguishes it from near-siblings like get_system_health and get_system_routerboard by content. It stops short of naming those siblings explicitly, so differentiation is inferential rather than stated.

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?

The note about reading free-memory/total-memory and cpu-load 'before blaming the network for a slow device' supplies an implied scenario for calling this tool. It never states when *not* to use it or points to an alternative diagnostic tool (get_system_health, get_system_routerboard), so usage is suggested rather than guided.

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