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

No annotations are provided, so the description must cover behavioral traits. It does disclose key behaviors: namespace-agnostic parsing, normalizing single-line documents to arrays, and reporting amount mismatches via warnings instead of returning wrong totals. However, it does not mention error handling, rate limits, or other operational specifics, which is acceptable given no annotations but still some gaps exist.

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 few functional sentences, front-loaded with the core purpose and behavior. The third sentence about 'engineering time' is a few rhetorical flourish that does not add operational value, making it slightly less crisp but still efficiently structured.

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?

Given a single parameter, no annotations, and no output schema, the description covers essential what the tool does and critical anticipations: defines the output categories, explains normalization policy, and warns about amount mismatch. It lacks a sample output format and error handling notes, but for the complexity level, it is reasonably complete.

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 only parameter 'xml' is fully described in the schema with 100% coverage. The description adds behavioral context about processing the input (namespace handling, normalization) that goes beyond the schema description, providing some added meaning about how the input is interpreted.

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 explicitly states the tool parses UBL-TR e-Invoice or e-Archive XML into clean JSON and specifies the output includes parties, line items, taxes, and totals. This clearly distinguishes it from sibling tools like tr_invoice_build (building invoices) and other validation tools.

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 implies the tool is for parsing e-Invoice XML but does not explicitly state when to use it vs. alternatives. It does not mention counterpart tools like tr_invoice_build or what should be used for building invoices, leaving usage context implicit.

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