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

Annotations only declare it is a non-destructive write; the description goes further by disclosing the initial state (always planned), the ruleset validation that occurs during a workflow run, and the refusal semantics when a Must rule fails. It does not cover permissions or return behavior, so it is strong but not exhaustive.

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?

Three dense sentences, front-loaded with the core action and precondition before the ruleset nuance. No filler, though the ruleset clause is long and would benefit from slight tightening.

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 creation tool with no output schema, the description covers precondition, initial state, and validation behavior. It leaves the return payload unspecified, but the requestId schema field partly compensates on the idempotency side, so the gap is minor.

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%, including the requestId idempotency contract and the size enum, so the schema already carries parameter meaning. The description adds no parameter-level detail (e.g., which project/batch pairing is valid), so baseline 3 applies.

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 ('Create a Work in a Batch') plus the precondition that the Batch must not be ready, and explicitly contrasts the initial state with begin_work. An agent can distinguish it from begin_work, create_batch_plan, and update_work without opening schemas.

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 a clear when-to-use condition ('a Batch that is not ready') and names the alternative that handles the next step ('begin_work starts it'). It stops short of naming exclusions such as when to prefer create_batch_plan or what to do if the Batch is already ready.

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