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

Discloses the real-world side effect the annotations can't capture: creators will be emailed by the selected campaign, plus it's free. That is exactly the extra context an agent needs before flipping the switch. It stops short of covering failure behaviour or what happens if the referenced campaign is invalid.

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: what it controls, the mode matrix, the safety instruction. The critical 'ask the user first' warning lands before the trivial 'Free' note.

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?

Covers purpose, mode semantics, and the user-facing consequence of enabling, which is sufficient for a single required boolean flag with no output schema. Minor gap: no mention of behaviour when provider/campaign_id are invalid or when no previous campaign exists for the re-arm path.

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 only 50%, and the description compensates by explaining the three meaningful combinations of enabled, provider and campaign_id – semantics the bare schema can't express. The remaining parameters (uid, bearer_token, idempotency_key) are already documented 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?

States a specific verb and resource (turn automatic sending of new leads to an outreach campaign on/off) and names the lead sources it covers (chat searches, run_ugc_agent, automations, applications). This clearly separates it from send_leads_to_campaign, which sends a specific batch manually.

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?

Gives concrete mode-selection rules: enabled=true plus provider and campaign_id targets a campaign, enabled=true alone re-arms the last one, enabled=false disables. It also mandates asking the user first. It doesn't name the sibling tool to use instead for one-off manual sends, so it falls short of a 5.

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