Batch operations

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

Goes well beyond the annotations: it discloses sequential ordering, fail-fast termination at the first error, and explicitly that earlier operations are NOT rolled back — the exact partial-failure semantics an agent must know before batching destructive writes. This is precisely the kind of behavior annotations cannot express.

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?

Front-loaded with purpose and the critical failure-semantics caveat before the payload format, then closes with a concrete two-step example. Every sentence carries information; nothing is redundant with the schema or annotations.

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 parameterless-return dispatcher with no output schema, the description covers ordering, failure behavior, op naming, and result referencing. It leaves the response shape on partial failure (what the caller gets back after the stop) unstated, which is the one gap worth closing.

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%, yet the description fully specifies the item shape ({'op','args'}), the naming convention that maps 'op' onto sibling tool names (tool name minus the 'cavalry_' prefix), and the '$<index>' result-referencing syntax including path traversal ('$2.created.0.id'). That reference syntax is not derivable from the schema and is essential to using the tool correctly.

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 ('run several operations in one round-trip, in order') and is immediately distinguishable from every single-operation sibling, since it is the only tool that composes them. An agent can tell this is a meta-dispatcher without opening the schema.

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?

The framing 'run several operations in one round-trip' clearly signals the condition that selects this tool over the individual siblings, and the ordering/atomicity note adds operational context. It stops short of an explicit exclusion (e.g. 'use the individual tool when you only need one operation'), so it falls just short of 5.

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