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

Beyond the annotations it discloses real behavioral traits: a $0.001 per-call cost that is waived on failure, the fact that datev/fec settings are persisted 'for the next export' (explaining the non-readOnly, non-idempotent hints), and that no tax returns are filed. It does not describe the failure modes, the download link's lifetime, or how long generated files persist in the store.

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?

One long comma-chained sentence with three 'or ... or ...' parentheticals buries the core purpose behind the return-value framing. Every clause carries information, but the structure is not front-loaded — an agent must read the whole paragraph to learn what the tool does.

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?

With five parameters, nested objects and no output schema, the description covers the return artifact, the cost model, and the settings-persistence side effect, which is most of what an agent needs. It leaves gaps on the exact file naming/expiry and on default date ranges for the non-datev formats.

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 already 80% with rich nested descriptions, and the description still adds cross-parameter meaning: datev defaults 'the year so far', fec covers 'the fiscal year that holds to' with every entry, and journal spans from-to. It clarifies which nested object (datev/fec) applies to which `what` value and that those settings are reused, though it doesn't explain the `from`/`to` defaults for journal/accounts.

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 concretely enumerates the four exportable artifacts (journal CSV, accounts chart, DATEV Buchungsstapel, FEC) and states the output is a file in the file store with a download link, so the resource is unambiguous. It never names the sibling exports/reports (books_report, tables_export, inventory_export) or explains how this differs, so sibling differentiation is absent.

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?

It gives solid audience-based selection cues for the `what` enum (accountant/program, German tax adviser, French tax audit, UK VAT MTD bridging software), which effectively says when to pick each format. It gives no guidance on when NOT to use this versus books_report or the other export tools, and no prerequisites for obtaining the datev/fec settings beyond 'needs the ... settings once'.

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