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

Annotations only declare it is not read-only and not destructive; the description adds the real behavioral payload: the run is pinned to the workflow's current revision, it returns its current step, a batch start skips the review step, edgeId can name the Batch stage route, retries against an open run return the same run, and a Batch run governs that Batch's Work queue. It even discloses the document dedup rule (re-sent documents return as uri references).

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?

The purpose and main input branches are front-loaded, and nearly every sentence carries distinct edge-case information. The single dense paragraph packs a lot of conditional clauses together, which slightly hurts scannability but wastes little.

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 6 parameters, nested objects, and no output schema, the description carries the return-value burden and does state what comes back (the current step) along with side effects on the Work queue and revision pinning. Error conditions and the precise shape of the returned step are not covered, which is the main residual gap.

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 description coverage is 100%, so the baseline is 3, but the description adds semantics the schema does not: it explains how the batch object is used (planned and run started in one call, review step skipped) and what edgeId means (the Batch stage route). It does not explain the batch name pattern constraint, leaving that to the referenced create_batch_plan.

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 (start a run of one workflow) and enumerates the three valid starting points: an Idea, a planned existing Batch whose Work has not begun, or a new batch plan. It also names the contrast case (a workflow that starts at Delivery takes none of them) and the sibling tools that complete that path, so an agent can pick it apart from create_batch_plan and create_delivery.

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 clear selection logic across the mutually exclusive inputs and points to create_delivery/update_delivery for the Delivery-start variant, plus a retry-idempotency note. It stops short of explicitly contrasting with resume_workflow, cancel_workflow, or begin_work, so the when-not-to-use side 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.