api_batch

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

With no annotations provided, the description carries the full behavioral burden. It discloses ordered execution, early termination on first failure, partial results, side-effect persistence via 'No rollback,' and the authority equivalence to api_invoke. It does not describe the return/error shape, but the provided behavioral traits are substantive and non-obvious.

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 compact sentences, each earning its place: core behavior, reference syntax, array syntax, expect semantics, and authority/risk. The main behavioral statement is front-loaded, and there is no redundancy or 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?

Given the nested ApiStep schema, no annotations, no output schema, and a large sibling list, the description covers the critical execution semantics, reference semantics, and side-effect behavior. Missing an explicit example or return/error shape, but the description is substantially complete for a tool of this complexity.

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 0%, and JsonValue is an empty definition, so the description must compensate. It does by explaining handle/ref/constant syntax, typed array variants, and the practical meaning of expect values. It does not elaborate on action or member semantics, but the most opaque parameter semantics are covered.

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?

The description opens with a specific verb and resource: 'Execute up to 100 ordered SDK steps; stop on first failure and return partial results.' This clearly distinguishes api_batch from single-step tools like api_invoke and other SDK operations.

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?

Usage context is implied rather than explicit. The description explains batch ordering and no-rollback behavior, and mentions 'same unrestricted local COM authority as api_invoke,' but it never explicitly states when to choose this tool over api_invoke or when not to use it. The expect guidance is parameter-focused, not tool-selection guidance.

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