set_networks

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

Beyond the annotations (not read-only, open world), the description discloses two critical behavioral traits: the tool refuses any request to enable a network, and it can act autonomously when spend clears the policy threshold with no conversions. These are non-obvious behaviors that an agent must know before calling the tool.

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?

Two sentences with no filler. The main action is front-loaded, followed by the one-way constraint and the autonomous trigger. Every clause adds distinct value, and the structure is easy to scan.

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?

The output schema covers return values, and the description explains the core behavior and constraints. The only minor gap is the lack of explanation for generic parameters (run_id, dry_run, rationale), but their names and defaults make them interpretable. Overall, an agent can safely invoke the tool with the information provided.

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?

With 0% schema description coverage, the description carries the burden of explaining parameters. It directly ties 'Display expansion' and 'search partners' to the boolean flags search_partners and display_expansion, and clarifies that true is not allowed (enable is refused). This is essential semantic meaning absent from the schema. Generic params like run_id, dry_run, and rationale are not described, but their names and defaults are self-explanatory.

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 specific verb and resource: 'Turn Display expansion and/or search partners OFF for a search campaign.' It precisely identifies the action and target, distinguishing it from sibling tools like pause_keywords or remove_campaign. The one-way constraint further clarifies what the tool is for.

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 description explicitly states the when-not-to-use condition: 'Can only switch networks off, never on — a request to enable one is refused.' This is a clear usage boundary, though it does not name an alternative tool for enabling networks. The context is clear but lacks explicit routing to siblings.

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