Many writes, one transaction

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

Discloses critical behavioral traits: all-or-nothing transaction with first-failure rollback and error naming, reply format ({id, seq}), and that rows are not returned. This goes well beyond the annotations, which only hint at idempotency and non-destructiveness, adding real operational context for the agent.

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 dense sentences, each earning its place: purpose, command format, transaction semantics, and response format. No filler or redundancy; the description is front-loaded with the most important constraint (ONE transaction, up to 200 writes).

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 complex batch tool, the description covers the essential operational aspects: usage examples, command schema (via reference to sibling tools), transaction behavior, failure reporting, and response format. The presence of an output schema reduces the need to detail return values, and annotations handle safety hints.

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 67% (actor lacks description), but the description compensates by fully explaining the 'commands' array structure, linking each command to the corresponding single-write tool and enumerating the 'type' values. It also clarifies command_id as an idempotency key. The actor parameter remains undocumented in text but is self-evident via its enum.

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?

Specific verb+resource+scope: 'Apply up to 200 writes in ONE transaction' clearly states the batch-write purpose. The description explicitly differentiates from single-write tools with 'instead of one call per row' and lists the four supported write types, making the tool's role unmistakable.

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?

Provides explicit use cases ('seeding an app' or 'filling a board in one go') and contrasts with alternatives ('instead of one call per row'). It also identifies the 200-write limit and implies when the tool is appropriate by mapping commands to the single-write tools.

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