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 richly: it discloses that it never reaches a real buyer, that some transports really submit the UBL to a partner's Peppol sandbox addressed to W System's own sandbox company, the side effects of each transport value, and the signed evidence receipt output. This is unusually complete behavioral disclosure.

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 critical constraint (SANDBOX ONLY) is front-loaded and the pipeline is laid out in sequence. It is dense with parenthetical asides and long run-on sentences, but nearly every clause adds operational information 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 no-annotation, no-output-schema, nested-object tool, the description is sufficient: it describes the pipeline, the transport-dependent side effects, and what is returned (evidence receipt JWS, partner document id). An agent has what it needs to call it correctly.

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 0%, so the description must compensate, and it does for 'transport', spelling out the meaning and effect of each value ('mock' simulated/default, 'recommand', 'e-invoice-be' with real sandbox submission and partner document id returned). The 'invoice' parameter is only referenced indirectly as 'same JSON as create_einvoice', leaving its internal semantics to another tool.

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 (send) and resource (e-invoice) with an explicit scope qualifier (SANDBOX ONLY) and enumerates the exact pipeline it runs. It explicitly relates to the sibling create_einvoice by noting it takes the same JSON, so an agent can place it without ambiguity.

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?

Clearly states the intended context: 'Use it to build and test an integration before live sending exists,' which tells the agent when this tool is appropriate. It does not name an alternative live-send tool or state exclusions, but the sandbox framing provides strong usage context.

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