extract_invoice_data

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

With no annotations, the description carries the full burden and does so well: it discloses that XML content is never logged or persisted, that missing fields return None instead of raising, that file_path is checked against FATTURAPA_ALLOWED_ROOTS before any read, and it enumerates the exact exception types. This is materially richer than a bare 'extract' claim.

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?

Front-loads the one-line purpose, then uses conventional Args/Returns/Raises sections, so it is skimmable. The Raises block is slightly heavy for a read-only parse, but every sentence conveys contract detail rather than filler.

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 two-parameter parse tool with an output schema, the description covers input sourcing, the allow-roots security gate, None-on-missing semantics, and all failure modes. An agent has everything needed to call it correctly; only the dual-input precedence edge case is unaddressed, and the output schema handles the return shape.

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 0%, so the description must compensate, and it defines both parameters (raw validated XML string; optional path validated against allowed roots) plus a ctx argument that appears only in the prose. It stops short of stating precedence when both xml_content and file_path are supplied.

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?

States a specific verb and resource: 'Extract key fields from a validated FatturaPA XML document,' scoping output to header + first body section. The word 'validated' hints that validate_invoice is a prerequisite, but no sibling is named explicitly, so the agent must infer the pipeline position.

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 a real usage fork: pass xml_content to skip file I/O, or file_path to read from disk. However it never states when to prefer this tool over find_invoice_anomalies or generate_invoice_report, and the validation prerequisite is only implied by the adjective 'validated' rather than stated as a condition.

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