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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds the useful behavioral detail that output is a flat CSV with either one row per line item or one row per document. However, it does not disclose input handling, failure modes, or anything beyond the output shape.

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 tight sentence that front-loads the output format ('Flat CSV') and then succinctly states the two possible row granularities. There is no verbosity or redundant detail.

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?

The schema and annotations cover a great deal: parameter types, formats, size limits, and safety. However, the description does not make explicit that one of file_base64 or path must be provided, even though the schema marks both as optional. This is an implicit precondition an agent could easily miss when calling the tool with no arguments.

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 level parameter already explains the 'lines' and 'documents' modes. The description's phrase 'one row per line item, or one row per document' merely paraphrases the schema's own parameter documentation rather than adding new meaning. The file_base64 and path parameters are also already well described in the schema.

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 clearly identifies the resource (invoice) and output format (flat CSV), and distinguishes the two row granularities. It lacks an explicit action verb like 'export' or 'convert', and it does not explicitly differentiate from siblings such as invoice_to_html or invoice_to_datev, though the CSV format makes the distinction fairly obvious.

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?

There is no guidance on when to use this tool versus alternatives like read_invoice, validate_invoice, invoice_to_html, or invoice_to_datev. The use case is only implied by the tool name and the word 'CSV'; no explicit conditions, exclusions, or prerequisites are provided.

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