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

Annotations only cover the generic safety profile; the description adds the operationally critical facts an agent cannot infer: real outbound email is sent, credits are consumed, user confirmation is mandatory, and two named failure modes with their response flags (warming:true, credits_required:true). It also spells out the semantics of the terms acceptance.

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?

Front-loaded with the highest-stakes fact (sends real email, uses credits) and every sentence carries operational content. It is dense with parentheticals and the terms clause is a long run-on, but nothing is redundant.

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?

No output schema exists, and the description compensates by documenting the two error payloads and their flags, plus the confirmation and consent requirements. An agent has everything needed to call this safely and handle its failure paths.

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 67% and accept_sending_rules has no schema description at all, yet the description fully defines it (agreement to the outbound-beta terms with concrete obligations). accept_warming_risk is given both meaning and a gating condition, which goes well beyond the schema's one-liner.

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 pair and resource ('Start or resume a campaign') and immediately clarifies the action's nature: it SENDS real email and consumes credits. That framing separates it from create_campaign (draft creation) and pause_campaign without needing to name them.

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 an explicit precondition ('Confirm with the user first'), a conditional branch for the warming failure with the exact remedy (set accept_warming_risk=true only after explicit agreement), and names the alternative tool to use when credits are missing (create_credits_checkout). This is when/when-not/alternatives in full.

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