create_purchase_order

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

All four annotations are false, so the description carries the behavioral burden — and it delivers: it discloses the Order-class voucher classification, the voucher-type-active prerequisite (confirmed live), the live failure mode for missing dueDate, and Auto Retain numbering behavior. The main gap is that some details are cross-referenced ('same reasoning as create_sales_order') rather than self-contained, so the agent must look to sibling definitions for full specifics.

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 sentences, roughly 115 words, with zero filler: definition, sibling differentiation, follow-up workflow, then prerequisites and required fields. It is front-loaded with the most important positioning. The final sentence is slightly dense with stacked cross-references, but every clause earns its place.

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 write tool (6 top-level params, 9 item sub-fields) with no output schema and all-false annotations, the description covers the essentials: what the voucher is, where it sits in the workflow, prerequisites, and required fields. What remains unspecified is the success envelope (there is no output schema) and the exact meaning of the referenced Auto Retain numbering behavior, though the schema's voucherNumber note partially compensates.

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 100%, with richly detailed parameter descriptions (godown auto-fill logic, batchName default, the EXCEPTIONS:1 recovery hint on voucherNumber, and dueDate's exact Tally error message). The description re-emphasizes that orderNumber and dueDate are REQUIRED and explains their provenance, which is useful reinforcement but not additive semantic content beyond the schema. Baseline 3 is appropriate.

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 opening sentence defines the tool precisely: 'Create a Purchase Order in TallyPrime — a future commitment to buy, before any goods move or invoicing happens.' It names the verb, resource, and the business moment in the purchase lifecycle, and immediately distinguishes it from siblings by calling out that create_purchase_invoice/create_receipt_note are different voucher types.

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 explicitly routes the agent: same item-line shape as create_purchase_invoice/create_receipt_note but with VCHTYPE 'Purchase Order', plus a sequenced follow-up instruction — 'Follow up with create_receipt_note (goods in) and/or create_purchase_invoice (billing)' once goods arrive. It even cross-references the voucher-type-active prerequisite from create_delivery_note, giving the agent concrete when-to-use and operational context.

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