Automations

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

Annotations only flag destructive/openWorld/non-idempotent; the description adds far more: dry_run never writes, run writes with one undo_id per rule, run errors unless every rule succeeded and reports succeeded/partial/failed, failed rows retry from the failed step, scheduled occurrences only count as fired when fully successful, and expected_revision guards against concurrent overwrites. This is exactly the behavioral depth annotations cannot carry.

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?

It is long, but for a 15-action tool with a nested rule grammar the density is largely earned, and it is front-loaded with the core purpose before descending into rule structure and action semantics. A few clauses (e.g., the step-ordering narrative) could be tightened, but nothing is filler.

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 no output schema, 14 parameters, nested objects, and destructive actions, the description carries a heavy load and does so: it covers rule grammar, all actions, run status semantics, retry behavior, and revision safety. An agent has enough to select an action and invoke it correctly.

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 86%, so the baseline is 3, but the description meaningfully supplements the near-empty `rule` object by specifying its shape (when/schedule/actions/then, marker requirement, action ordering) and explains confirmed-vs-merge update semantics and the revision/edit contract. It adds real meaning beyond the schema's `additionalProperties: {}` without fully specifying every field's syntax.

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+resource ('Manage and run automation rules') and grounds it in concrete state (rules.json or NOTION_PLUS_RULES), which no sibling covers. It even positions itself relative to siblings by noting the `when` condition reuses notion_query's where/filter and `then` reuses notion_build_report args, making its scope unambiguous.

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?

The description enumerates every action (list, get, add, update, validate, dry_run, enable, disable, delete, run, history, waive, export/import, deploy) with a short gloss of what each does, which is strong per-action usage context. It stops short of explicit when-to-use-this-vs-a-sibling routing (e.g., vs notion_bulk_update or notion_undo), so it is clear rather than exhaustive.

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