whatsapp_campaigns_write

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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds crucial non-obvious behavior: run sends real messages that Meta bills, dryRun previews without sending, and create leaves the campaign stopped until run. The billing and approval-state consequences are exactly the kind of value that annotations cannot convey.

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-loads the definition and the dryRun warning before the field listing and action table, so the highest-risk information is seen first. The dense parenthetical field enumeration is slightly heavy but each item carries actionable detail.

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?

For a destructive, non-idempotent mutation tool with a nested campaign object and no output schema, the description covers required fields, action prerequisites, and the safety workflow. Minor gaps remain around what run/delete return and error conditions, but nothing critical to invoking it correctly 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?

Despite only 67% schema coverage, the description enumerates the campaign fields (leadGroupName or "all", phoneId, templateId/Name/Language/Category, variableMapping, headerVariableMapping, delayBetweenMessages default 2, openTime/closeTime, timezone) with enough semantics to construct a payload. It also clarifies campaignId is required for update/delete/run and that dryRun applies to run.

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 set (create, edit, delete, send) and resource (WhatsApp broadcast campaign), then defines the resource precisely as an APPROVED template sent to every lead in a lead group. This makes it clearly distinguishable from siblings like campaigns_write and whatsapp_campaigns_read.

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 a concrete operational rule: always run with dryRun=true first and confirm the audience with the user before sending. Each action lists required fields, so the agent knows what to supply. It does not explicitly say when to prefer a sibling tool over this one, which keeps it from a 5.

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