create_sales_invoice

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

Annotations only say readOnlyHint=false and destructiveHint=false, which is thin; the description carries the full burden and delivers exceptional value. It discloses a confirmed-live behavioral hazard — vouchers becoming undeletable via API when shared party/stock items are used across Sales and Purchase invoices — plus the exact recovery path (Company Data → Rewrite) and the confirmation that it is not a permanent lock.

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?

Three sentences, zero filler, and the core purpose is front-loaded before the sibling distinction and the warning. The warning is long but every word earns its place — it conveys a live-confirmed failure mode and its workaround, which is exactly the kind of content that must not be trimmed.

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 16-parameter mutation tool with no output schema, the description covers core function, sibling differentiation, and the critical lock hazard; the schema covers every parameter exhaustively. The only gap is that no explicit success-return shape is stated, though the schema's CREATED:0/EXCEPTIONS:1 hints let an agent infer the Tally gateway response pattern.

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 100%, so the schema already documents all 16 parameters in rich detail (including failure modes like the godown silent fail), putting this at the baseline 3. The tool description adds mild structural meaning — per-line salesLedger vs. one VAT line on the total — but does not meaningfully compensate beyond what the schema already provides.

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 ('Create an item-invoice Sales voucher in TallyPrime') with concrete detail about what it produces: stock item lines with quantity/rate, each posted to its own Sales ledger, plus an optional VAT/tax line. It explicitly names the confusable sibling and its limitation ('Distinct from create_voucher, which only supports plain ledger-to-ledger entries with no stock items'), so an agent can tell it apart without opening schemas.

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?

Gives an explicit when/hen-not: use this for item-invoices with stock item lines, and names create_voucher as the alternative for plain ledger-to-ledger entries. The live warning about the same party/stock item appearing in BOTH a Sales and Purchase item-invoice also implicitly guides when NOT to combine this tool with create_purchase_invoice on the same masters.

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