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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, and the deterministic generation behavior is consistent with them. The description adds the algorithmic context (check digit plus optional length digit), but gives no information about return format or how errors are reported, which matters since there is no output schema.

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?

A single front-loaded sentence that wastes no words; purpose and output are stated immediately with no filler.

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 small two-parameter generator the purpose is complete and safety is covered by annotations, but with no output schema the description never states the format of the returned reference, which an agent needs to use the result.

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 the schema documenting both base ('digits') and length_digit ('true' to add length digit), so the schema does the heavy lifting. The description adds only a marginal example ('such as an invoice number') and restates the optional length digit, so it stays at the baseline.

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 ('Generate a Swedish OCR reference') and elaborates on exactly what is produced (check digit, optional length digit) from a base number. The generate-vs-validate verb split cleanly distinguishes it from the sibling validate_ocr.

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 phrase 'such as an invoice number' implies the intended input context, so usage is inferable, but there is no explicit when-to-use/when-not guidance and no pointer to the complementary validate_ocr sibling. Adequate but with clear gaps.

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