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

Annotations already mark this as read-only and idempotent; the description adds meaningful behavior beyond that: the wrapped endpoint, the required permission ('devices'), and the in-tool aggregation logic including severity breakdown and top-N calculation. No contradictions 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?

Three tight sentences: use case, endpoint + aggregation behavior, and sibling navigation. Every sentence earns its place and the most decision-relevant information is front-loaded.

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 single-optional-parameter summary tool, the description covers the use case, endpoint, permission requirement, output dimensions, and the key sibling alternative. Even without an output schema, an agent has enough to select and invoke the tool correctly.

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%, so the baseline is 3, but the description adds real value by clarifying that top_n refers to 'top-N devices by alert count,' resolving the otherwise ambiguous 'loudest' terminology in the schema.

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 purpose ('high-level network health snapshot'), a concrete underlying endpoint, and the exact aggregate outputs (device count, active alert count, top-N devices). It also positions itself against the sibling device_get by presenting the tool as a summary view rather than a drill-down.

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 explicitly scopes the tool to 'how's the network?' style questions and tells the agent to use device_get for specific-device drill-down. It does not enumerate every alternative like alerts_list or device_list, but the primary routing guidance is clear.

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