erpnext_batch_prepare

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

Annotations (destructiveHint=true, readOnlyHint=false, idempotentHint=false) already signal the safety profile, and the description adds meaningful behavioral traits beyond them: batches are explicitly non-atomic and stop on error, source count verification is performed, and a single user confirmation covers the whole batch. These are genuine operational disclosures that shape how an agent invokes and monitors the tool.

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?

The description is compact and front-loaded: the core purpose appears in the opening sentence, followed by the binding example and the critical non-atomicity caveat. Every sentence earns its place; there is no filler or repetition of schema content.

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 destructive, non-idempotent tool with a complex requests array parameter, the description covers key behaviors (count verification, confirmation, non-atomicity) and an output schema exists, so return values are covered. Still, it lacks guidance on side effects of 'prepare' in the broader flow, the distinction from erpnext_batch_prepare_from_artifact, and what differentiates this from execution tools — leaving meaningful gaps for an agent navigating the sibling set.

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%, so the description must compensate — it does for the bindings parameter via a concrete example ({'/doc': {'step': 0, 'pointer': '/data'}}) that explains the response-to-request pointer mechanism. However, the primary parameters requests, expected_count, and label are only indirectly referenced through 'exact ordered batch' and 'Verify source count'; the description adds meaning for one nested parameter but leaves the others to inference.

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 states a specific verb and resource: 'Prepare an exact ordered batch' — clear and unambiguous about the object and scope, with qualifiers ('exact', 'ordered') that add precision. However, it does not explicitly differentiate from the sibling erpnext_batch_prepare_from_artifact, which appears to be an alternative preparation path, so the distinction is left to the agent.

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 description gives no explicit guidance on when to use this tool versus alternatives such as erpnext_batch_prepare_from_artifact, erpnext_plan_execute, or erpnext_api_request. Notes like 'one user confirmation covers the batch' are contextual but do not tell the agent which sibling to select under which conditions, so the agent must infer usage from purpose alone.

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