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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true and openWorldHint=true, so the safety and idempotency profile is covered structurally. The description still adds real behavioural context beyond that: the dry-run first call, the exact-match guarantee between preview and sent text, the 50-message preview cap, and the disabled-Sending error path. Three rather than five because the description does not say what happens to the rest of the queue after the window moves, or how partial sends are reported.

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?

It is front-loaded with the action, then the two-phase flow, then the edge cases, and every sentence carries information. The product-name-heavy clauses ('as Send in its Ready to send does', 'in Sergio') are harder to parse than the rest and could be tightened without losing meaning.

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?

There is no output schema, and the description compensates by describing what the preview contains (each person and their exact finished text, up to 50 at a time), the confirm_token it returns, and what the disabled-Sending response looks like. For a three-parameter mutation tool with a confirmation gate, nothing an agent needs is missing.

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 both confirm_token and idempotency_key already carry their own descriptions that say nearly the same thing the prose does. The description's added value is the constraint that the retry must reuse the SAME idempotency_key alongside identical arguments, and that campaign_id must refer to a started campaign — useful but marginal over 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 first sentence names a specific verb and resource (sends a started campaign's drafted messages that are ready) and constrains scope with the send window and the business's Sending setting. An agent can tell this apart from start_campaign or send_text, since the object is a campaign's queued drafts rather than a new or ad-hoc message.

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 gives an explicit two-call procedure: first call without confirm_token returns a preview and nothing is sent, second call with the same arguments, the same idempotency_key and the confirm_token performs the send. It also states the precondition (the person must say yes, after seeing the preview verbatim) and the failure branch when Sending is off, plus who can turn it on.

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