get_device_sdwan_monitor

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

With no annotations, the description carries the burden and does well: it explains that the call proxies the live device monitor API through FortiManager (implying a managed, reachable device), enumerates the two proxied endpoints fetched, and names the return keys including error/error_code. It stops short of stating failure modes such as an offline device or permission requirements, so not 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?

Front-loaded with the verb/resource and the key contrast before the endpoint bullet list and Args/Returns blocks. Reasonably efficient, though the Args/Returns docstring sections partially restate structured fields and could be trimmed.

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 two-optional-parameter read tool this covers the essential gaps left by an annotation-free, description-less schema: what is fetched, the two data sections, the summary key, and error handling. The Returns section duplicates the existing output schema, which is mild redundancy rather than a gap.

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 compensate, and it does: it documents that adom defaults to DEFAULT_ADOM/'root' and device defaults to DEFAULT_DEVICE, plus a concrete example name and the case where device becomes required. Only the expected format/validation of adom names is left implicit.

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 (read) and resource (device's LIVE SD-WAN Monitor status) and explicitly contrasts itself with the sibling get_device_sdwan, which reads config rather than runtime state. An agent can distinguish the two without opening either schema.

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?

Names the alternative (get_device_sdwan) and the condition that selects it — config vs runtime state — and gives a concrete user question ('how are the uplinks doing right now / which member is breaching SLA') that only this tool answers. Routing is unambiguous.

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