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

Adds substantial context beyond the annotations: real emails and approvals are sent, execution is all-or-nothing (an out-of-scope or invisible item starts nothing), the runIds are returned, and permission is automation.manage (or org MANAGER+ for org-wide workflows). The only weak spot is that repeated invocation appears to spawn fresh runs, which sits uneasily with idempotentHint=true and is not clarified.

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 the action and mode branching, and every clause contributes facts an agent needs (scope, limits, permissions, return value). The two long semicolon-chained sentences pack a lot in but are denser than ideal and could be split for faster scanning.

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, open-world mutation with no output schema, it covers everything material: what is executed, per-mode behavior, atomicity guarantees, authorization requirements, the off-switch case, and what the call returns (runIds) with a pointer to the monitoring tool. Nothing an agent needs to invoke it safely is absent.

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 0% schema coverage the description carries the load and mostly does: it maps kind values to id semantics (task ids vs document ids), notes the 50-item ceiling matching maxItems, and ties workflowId to a project scope and permission domain. It never says what a document-kind call returns differently or what happens to already-run items, so a little meaning is still missing.

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?

Opens with a specific verb+resource ("Run an active workflow for real on chosen items") and the phrase "for real" implicitly separates it from test_run_workflow. It then spells out the two execution modes (one run per task, one per document as an approval send), so an agent can distinguish it from cancel/list/get workflow-run siblings.

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 explicit conditions per mode: kind "task" with up to 50 task ids, or kind "document" which requires the workflow to be on a document trigger and Business+ for document approval. It also names list_workflow_runs as the monitoring follow-up, and states the operator-switch and permission preconditions that would cause a refusal.

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