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

Annotations only say it is a non-destructive write; the description goes far beyond that by explaining the observable effect (fetch/XHR calls wait or fail, offline rejects every call), that the numbers are simulation settings rather than real measurements, that mock rules override it, and that the change is logged in device_log as simulated.

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 most important information (what it does and the valid values) is front-loaded, and each subsequent sentence adds a distinct fact: effect on requests, simulation caveat, mock precedence, error, logging. It is slightly dense at six sentences, but no sentence is 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?

With no output schema and minimal annotations, the description carries the burden well: it covers effects, precedence with a related tool, the failure mode, and the audit trail. An agent has everything needed to invoke this correctly and interpret the result.

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% and the schema already lists the same profile values, so the description's enumeration is largely duplicative. It does add one piece of meaning beyond the schema — that an unrecognized name fails with unknown_profile — but the session parameter is left entirely to 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 opens with a concrete verb+resource ('Make the phone's network behave like a named profile') and immediately enumerates the accepted profile names, so an agent knows exactly what this tool changes. It is clearly distinguishable from the read-side sibling get_network_profile.

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?

Usage context is explicit — this simulates network conditions for an app's fetch/XHR calls, and mock rules from set_network_mocks take precedence, which tells the agent when this tool's effect will be overridden. It does not spell out a 'use this instead of X' rule against get_network_profile, but the write-vs-read split is obvious from the phrasing.

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