update_sales_invoice

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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=true, readOnlyHint=false) by disclosing the matching semantics (date + voucher number), the refusal behavior, and the underlying risk: 'Tally's Alter lookup ignores voucher type and can silently corrupt the wrong one — confirmed live.' This is exactly the hard-won behavioral context an agent needs to avoid a costly mistake, and it does not contradict the annotations.

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 dense sentences, each carrying load-bearing information: the mutation scope, the identity key plus prerequisite lookup, and the refusal/collision warning. The critical safety warning about silent corruption is front-loaded in the final sentence rather than buried, and there is no filler or repetition of schema fields.

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 16-parameter write tool with no output schema, this description covers the essential operational context: what gets replaced, how the target is identified, the prerequisite verification step, and the collision failure mode. The only meaningful gap is return-value behavior (nothing says what happens on success or when the voucher is not found), which the absent output schema leaves unstated.

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?

With 88% schema description coverage, the schema carries most parameter meaning, so baseline is 3. The description adds genuine value on top: it reveals that date and voucherNumber form a composite lookup key (the schema only labels them individually), and it cross-references create_sales_invoice so an agent can reuse its parameter knowledge. This lifts it above baseline, though it doesn't comment on every parameter.

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: 'Update an existing item-invoice Sales voucher in TallyPrime, replacing its item lines, party, and narration.' The scope of modification is explicit, and the sentence 'Same fields as create_sales_invoice, plus voucherNumber' positions it as the update counterpart to a named sibling, so an agent can distinguish it from create_sales_invoice and the other update_* tools 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?

Gives explicit preconditions and workflow: 'use get_ledger_vouchers or get_vouchers first to confirm it exists and is unique.' It also states a specific refusal condition — another voucher type sharing the same number on that date — and prescribes the remedy ('resolve the collision in Tally first'). The relationship to create_sales_invoice (same fields plus voucherNumber) implicitly routes new-voucher creation to the create sibling.

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