create_automation

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

Adds substantial behavior beyond the annotations (readOnlyHint=false, destructiveHint=false): http_request writes results back into columns, delay pauses and later resumes the action chain, network actions support retry with bounded attempts/delaySeconds, and send_webhook supports HMAC signing via config.secret. No contradiction with the annotations.

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?

Well front-loaded: purpose and the most valuable usage pattern first, then triggers, actions, and finally exceptional behaviors. It is long, but nearly every sentence carries information absent from the schema; only the trigger enumeration mildly duplicates what the schema's enum already provides.

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 complex tool (7 params, 5 required, nested objects, no output schema, 29% schema coverage), it covers a great deal: trigger and action vocabularies, retry and delay semantics, and HMAC signing. Gaps remain: triggerConfig needs for date_approaching and status_changed, the isActive parameter is never mentioned, and validation/error behavior is not addressed. Strong but not exhaustive.

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 only 29%, yet the description compensates strongly: it enumerates action types, documents the http_request config shape (url, method, responseMapping), delay config, retry bounds, and secret. Remaining ambiguities include the delay config notation ({ minutes | hours | days }) not stating the value shape, send_whatsapp appearing outside the main action list, and triggerConfig requirements for date_approaching/status_changed being undocumented.

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 opening sentence states a specific verb+resource: 'Create an automation on a board', backed by a plain-language definition ('when something happens, do something'). It is clearly distinguishable from siblings like list_automations, and the enumeration of triggers and actions makes the scope concrete.

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?

Provides concrete usage context: pairing http_request with the scheduled trigger to keep boards self-updating (prices, exchange rates, shipment status, weather), and using the delay action for reminders and follow-ups. It stops short of an explicit when-not-to-use or named alternative tools, but the guidance is specific enough for an agent to decide.

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