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

The annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is known; the description adds real context beyond that, namely that messages are queued to real customers from the business number, that owner approval and sms:write are required, and that re-launch of an in-flight campaign is rejected. It does not cover what happens on partial send failure or whether queued messages can be cancelled, which keeps it below a 5.

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, front-loaded with the action and its effect on customers, then prerequisites, then the failure condition. No filler and nothing repeated from the schema verbatim.

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 an output schema present and rich annotations, the description covers the essentials for a destructive, outbound-sending tool: what it sends, from where, under whose authority, and when it will refuse. Remaining gaps (irreversibility of already-queued texts, rate limits, per-recipient failure handling) are moderate but not blocking for correct invocation.

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%, so the baseline is 3; the description goes further by binding parameters to a workflow, specifically that the fingerprint and the milestones/minimumDays values must be those produced by preview_review. That constraint meaning (values must match the previewed payload) is a behavioral tie between parameters that the schema only states per-field.

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 names a specific verb and resource: 'Launches the approved review-request campaign, queuing text messages to the listed customers from the business number.' It also implicitly separates this tool from the preview/prepare siblings by requiring 'the fingerprint from preview_review', so an agent can tell this is the execute step rather than the dry run. It stops short of an explicit 'this is not preview_review' statement, so it lands just below the top mark.

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 preconditions: client owner approval, the sms:write scope, accepted=true, and a fingerprint produced by preview_review, which effectively tells the agent to run preview first. It also states an exclusion: 'A campaign that is already sending can't be launched again.' No alternative siblings (e.g. launch_email_campaign / launch_call_campaign) are named, so it is clear context without explicit routing.

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