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

Beyond the readOnlyHint annotation, the description discloses key behaviors: corrected data overrides original extractions, newest-first ordering, and one row per container/invoice line/package/goods line. These details are not visible in the schema or annotations and are valuable for invoking the tool correctly.

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 two sentences long, front-loaded with the primary purpose, and provides a clear alternative in the second sentence. It contains no filler or redundant phrasing.

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?

Despite having no output schema, the description explains the output format (normalized rows with granularity), ordering, filtering options, data precedence, and points to an alternative for other file types. This is sufficient for an agent to invoke the tool correctly in most scenarios.

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?

The input schema has 100% coverage for both parameters, with descriptions for each and an enum for type. The description only restates the existence of a doc_type filter and max_rows cap without adding extra semantic meaning. The baseline of 3 applies since the schema carries the explanatory burden.

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 states the tool's purpose: exporting completed extractions as normalized line rows for TMS/ERP use, with specifics on row granularity and ordering. It distinguishes itself from siblings like extract_batch or list_documents by focusing on the export of processed data in a structured format.

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 explicitly provides an alternative for CSV/XLSX files via the REST API, which helps the agent decide when not to use this tool. It also implies the appropriate use case (completed extractions, row-oriented output) without ambiguity.

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