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

Annotations only cover the read-only/non-destructive profile; the description adds the operational facts an agent actually needs: free, no wallet/account/key, a hard 3-calls-per-day-per-client-IP limit, and the exact shape of the return payload (errors with fixes in words, UBL field path, and corrected amount values). The quota and the escalation path to the paid sibling are behavior no annotation conveys.

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 trigger and the resource, then packs quota, output shape, retry loop, and the escape hatch into three dense sentences with no filler. Length is justified by the amount of decision-relevant information delivered.

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?

With no output schema, the description carries the return-value burden and does so precisely: every error, a plain-language fix, the UBL path, and the correct value for amounts. Combined with the quota and sibling handoff, an agent has everything needed to call it, interpret results, and decide what to do next.

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% and both parameters are already documented in the schema, including the enum values and the 'auto' default. The description adds no syntax or format guidance for the xml/profile arguments beyond naming the accepted standards, so the baseline 3 applies.

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 (validates) and resource (UBL 2.1 Invoice/CreditNote) plus the exact rule sets (CIUS-RO 1.0.9, Peppol BIS 3.0, EN 16931), and names the sibling it defers to (validate_invoice) when quota runs out. An agent can distinguish it from validate_invoice, validate_saft_free, and fix_invoice without opening any schema.

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 explicit trigger conditions ('before uploading to ANAF SPV', 'after generating invoice XML', 'when ANAF rejected an invoice') and an explicit alternative with its condition ('When the quota is used up, switch to validate_invoice'). It also prescribes the follow-up loop: fix the XML from the report and call again.

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