Create a DM automation (paused)

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

Annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=false; the description adds the crucial behavioral facts those annotations don't carry — the automation is created paused and answers nobody until enabled, the Draft scope is required, and retries with the same key are safe. It doesn't state what happens on ValidationFailure of sameKeywords beyond "say so", but the coverage is rich. No contradiction: idempotentHint=false describes default behavior, while the description explains idempotency is opt-in via the key.

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 purpose and the sibling distinction, then triggers, then steps, then operational rules. It is dense and long — a single run-on block covering triggers, steps, brand-voice advice, scope, approval flow and idempotency — but nearly every sentence carries non-redundant information.

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?

Given a complex tool with nested oneOf steps, 6 parameters, no output schema and no destructiveness annotations, the description covers what the agent needs: trigger semantics, step types and ordering, scope requirement, the paused-by-default behavior, the approval workflow and idempotency handling.

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?

With 67% schema coverage, the description meaningfully compensates by explaining each trigger type's constraints (comment_keyword needs a DM with a link; postIds "any" or "next"; ref_link uses exactly one channel; after_purchase events ["booking","sale"]) and the step vocabulary, including ordering rules like aiReply last and the fact that remove-tag/set-field/branch steps must be added in the app. It doesn't restate every nested field (e.g. likeComment, channelIds), relying on those schema descriptions.

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 ("Creates a DM automation on Instagram or Facebook") plus a crucial scope qualifier ("always paused: it answers nobody until it is switched on"). It explicitly names the sibling it is not — "an email series that starts by itself is postfjord_create_email_automation" — so an agent can route correctly without opening either schema.

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?

Explicitly says when to use it versus postfjord_create_email_automation, names the follow-up step (switch it on with postfjord_set_automation only after the person approves), and gives retry guidance with the same idempotency_key. Nothing about selection or sequence is left to inference.

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