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

Annotations only say this is a non-read, non-destructive mutation. The description adds substantial behavioral context beyond them: the run is pinned to the workflow's current revision, returns its current step, each instruction body is sent once per run, previously sent documents come back as uri references, the review step is skipped on the batch path, and a retry while the run is open is idempotent. This is unusually rich disclosure for a mutation tool.

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 source modes are front-loaded in the first sentence, and no sentence is filler given the tool's complexity. However, several sentences pack multiple unrelated facts (idempotency, review-step skipping, revision pinning) into dense clauses, which costs readability for a 6-parameter tool with three start modes.

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?

There is no output schema, and the description compensates by stating the return value (the current step). Combined with the source-mode coverage, idempotency, revision pinning, and the Delivery exception, an agent has everything needed to 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?

With schema coverage at 100%, the baseline is 3, but the description adds real meaning: it explains the mutually exclusive source inputs (ideaId/batchId/batch), that edgeId names the Batch stage route for the batch path, and that the batch object is a full plan (name + ordered works). That is value beyond the schema's one-line parameter descriptions.

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 possible sources (Idea, planned Batch, new batch plan), plus the Delivery-start exception where none apply. An agent can distinguish it from create_batch_plan, create_delivery, and assign_batch_to_delivery from the text alone.

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?

Explicitly names when this tool applies vs. alternatives: it points to create_batch_plan for the plan shape, and states that a Delivery-starting workflow takes none of the sources and is completed by create_delivery or assign_batch_to_delivery. The routing conditions are stated, not implied.

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