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

The annotations already convey safety (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description does not need to repeat that. It adds a behavioral note that the CSV is 'flat' and that granularity can be per line item or per document, but this largely restates the level parameter's semantics rather than revealing new behavioral traits.

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, compact sentence that front-loads the core output type ('Flat CSV of the invoice') and then immediately clarifies the two row modes. There is no filler or redundant repetition of schema details.

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?

Given the full input schema, an output schema, and read-only/idempotent annotations, the description is largely complete for a straightforward conversion call. It does not need to explain return values or safety. The only notable gap is the lack of anything pointing to when to choose CSV over sibling tools, but that is covered by the usage-guidelines dimension.

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 defines path, level, and file_base64, including formats and constraints. The description's line-item vs document phrasing mirrors the level parameter without adding new parameter-level meaning, so the baseline of 3 applies.

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 title and description together make clear that this tool exports an invoice as a CSV, with explicit row-granularity options ('one row per line item' vs 'one row per document'). It clearly identifies the output format and distinguishes it from sibling HTML/Datev converters, though it does not explicitly name the siblings or use a strong verb in the description itself.

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 no guidance on when to use this tool vs the sibling tools invoice_to_html, invoice_to_datev, read_invoice, or validate_invoice. There are no exclusions, prerequisites, or alternative-selection hints; an agent must infer usage solely from the tool name and title.

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