Workflows

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

Despite annotations already declaring destructiveHint=true and openWorldHint=true, the description layers substantial extra behavior: secrets are referenced as ${secret:NAME} and 'never stored or shown', http/slack are restricted to NOTION_PLUS_HTTP_ALLOW hosts, runs are durable and resume after the last finished step with double-create protection, and approval/delay pause until the next scheduler pass. This is exactly the kind of operational context 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?

Content is dense and mostly relevant, and the core purpose is front-loaded, but the body degenerates into a long semicolon-heavy run-on mixing step actions, reference syntax, durability, and action enums. It would benefit from paragraph or bullet structure; nearly every clause is useful but hard to parse as one block.

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 with 8 params, no output schema, and nested objects, the description covers triggers, step actions, reference variables, durability/idempotency, host allow-lists, approval/delay pauses, and the full action set. What is missing is per-action return behavior, but that is a modest gap given how much ground is already covered.

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 50% across 8 params. The description explains the `inputs` param ('run: values for ${inputs.*}') and extensively documents the `workflow` object's internal structure, but leaves run_id, event_id, limit, and status semantics to the schema. It adds meaningful value for the nested workflow spec but does not fully close the coverage gap.

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 gives a precise verb+resource: 'Multi-step workflows (version 2 of automations): a trigger (manual, schedule, or Notion webhook events) and typed steps run in order.' It names the sibling relationship to automations v1 via the 'convert (a v1 rule into a workflow)' action, so an agent can distinguish it from notion_automation without opening a 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?

Usage is implied through the enumerated actions (list, get, save, run, runs, resume, cancel, convert) and the mention that convert migrates a v1 rule, but there is no explicit 'use this instead of X when Y' routing against the obvious alternative notion_automation. The agent can infer the lifecycle but gets no exclusions or conditions.

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