create_credit_note

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

With annotations all false (no read-only, no idempotent, no destructive flags), the description carries the burden. It discloses that the tool reverses stock and revenue, mentions the dual-role deletion caveats, and provides a live confirmation of the stock quantity increase. This goes beyond the schema and gives the agent a realistic expectation of side effects, though it does not discuss reversibility or error behavior in detail.

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 a single, dense paragraph that front-loads the purpose and key distinctions. It is efficient but packs many details (sign pattern, live confirmation, caveats) into one block without bullet points or headings. It remains readable and not overly long, though a structured format could slightly improve scannability.

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 tool with 16 parameters and no output schema, the description provides essential context: it explains the accounting semantics, references shared caveats, and gives a concrete validation example. It does not describe the response format or error handling, but the reference to create_sales_invoice for caveats helps fill gaps. The agent would need to consult that sibling for full behavioral detail, so it is not fully self-contained.

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% and the schema descriptions are detailed (e.g., billType default, godown auto-fill condition, voucherNumber guidance). The tool description adds no new per-parameter meaning beyond referring to the sales invoice's caveats, so it does not need to compensate. Baseline 3 is appropriate because the schema already documents all parameters thoroughly.

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 action (create a Credit Note) with a clear resource (item-invoice in TallyPrime) and explicitly differentiates it from create_sales_invoice by the flipped debit/credit convention. It also clarifies it is a Sales return that reverses stock and revenue, making its purpose unambiguous among the many create_* siblings.

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 clear usage context: it is for sales returns, references create_sales_invoice for shared caveats, and notes the difference in sign pattern vs sales invoice. However, it does not explicitly state when NOT to use this tool or name alternative return tools (e.g., create_rejections_in) beyond the sales invoice reference, leaving some inference to the agent.

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