List network devices

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety and idempotency profile is fully covered without description help. The description adds the meaningful scope fact that these are network-monitored devices rather than agents, which is useful disambiguation. It says nothing about pagination defaults, the cost of the 'full' flag, or result ordering.

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?

A single sentence, front-loaded with the resource and immediately followed by the exclusion that prevents the most likely mis-selection. No filler and nothing to trim.

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 simple paginated read tool with a fully documented schema and complete read-only annotations, the description covers the one thing structured fields cannot: what this collection is versus the agent collection. No output schema exists, but the return shape is trivially inferable from the 'full' flag and page parameters.

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 100%, so all four parameters (type, page, itemsInPage, full) are already documented, including the enum values and the warning that 'full' produces much larger output. The description's enumeration of generic/TCP/SNMP/HTTP merely echoes the enum. Baseline 3 is appropriate.

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 names a specific resource ('network-monitored devices') and enumerates the four kinds (generic, TCP, SNMP, HTTP), so the agent knows exactly what set is returned. It also draws a boundary against a close sibling (agents installed on machines), which is the main source of ambiguity. The listing verb itself only appears in the name/title, not the description.

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?

It gives an explicit exclusion — 'not the agents installed on machines' — which effectively routes the agent toward list_agents for machine-installed agents. That is a real when-not statement rather than implied usage. It stops short of stating positive conditions (e.g., 'use this when you want to audit monitored network endpoints') or naming list_agents by name.

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