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

Annotations already declare read-only, idempotent, non-destructive. The description adds substantial behavioral context: it is 'not a thin keyword grep', nulls mean unknown, low-confidence totals should not be treated as ledger truth, and it fails closed with cost per successful response. No contradiction with annotations.

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?

Description is dense but purposeful: front-loaded output contract, then usage rule, input formats, and key behavioral caveats. Every sentence contributes, though a few details (e.g., 'still accept OCR text or image/PDF base64') overlap with the schema.

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 complex extraction tool with an output schema, this description is remarkably complete: it names the extracted fields, the warning type, the country scope, the input modes, the confidence/null semantics, and even the cost/failure behavior. Nothing required to select or call the tool is missing.

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 baseline is 3. The description reinforces that text OR file_base64 is accepted and maps to the oneOf, but does not add meaningfully deeper semantics for tier, filename, or content_type beyond the schema's own descriptions.

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?

Description states a specific verb ('Parse') and resource ('tax invoice or commercial invoice') and enumerates the concrete output contract (seller, dates, VAT, totals, warnings). It also explicitly distinguishes from till slips/receipts, helping differentiate from sibling parse.receipt.

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?

Gives clear usage condition: 'Use when the document is an invoice rather than a till slip.' It also mentions the input forms it accepts and the target geographies/AP automation context. It doesn't explicitly name sibling tools or exclusions beyond the till-slip case, but the guidance is sufficient.

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