run_batch

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

With no annotations, the description carries the full burden and does so well: it discloses sequential execution, first-error stopping by default, that partial results are returned in order, and critically that this is NOT a transaction (no rollback of succeeded steps). These are exactly the behavioral traits an agent needs before batching mutations.

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?

Four tight sentences, front-loaded with the core purpose, then error behavior, then the transaction caveat, then the rollback recommendation. Every sentence earns its place with no 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?

For a mutation-batching tool with no annotations and no output schema, the description covers execution order, error policy, non-atomicity, and rollback strategy. An agent has everything needed to decide whether and how to call it; return values are implicitly described as ordered partial results.

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 only 50%, so the description must compensate. It explains stopOnError's default and effect ('by default stops at the first error') and that partial results come back in order. The actions array's per-item shape ('action' + opaque 'payload') is left to the schema, but the description adds meaningful semantics beyond it.

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 mechanism: 'Execute multiple bridge actions in one round trip instead of one WebSocket call per action.' This distinguishes it clearly from the dozens of single-action siblings (set_fill_color, create_frame, etc.) by explaining the batching purpose rather than just naming it.

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 when-to-use ('multiple bridge actions in one round trip') and names a concrete alternative for the rollback case ('Use create_checkpoint first if you need a rollback path'). The stopOnError default is also explained, so the agent knows the two execution modes.

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