invoices_submit

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

Annotations already declare non-readonly, non-idempotent, open-world behavior; the description adds genuinely new context by naming the resulting state transition ('sent_to_provider') and disclosing that ANAF validation is asynchronous. It does not cover failure modes (duplicate submission, provider errors) or what the submit response itself contains, which keeps it from a 5.

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?

Three short sentences, front-loaded with the action and precondition, then the state effect, then the verification path. Every sentence carries operational information with no 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 state-changing, asynchronous submit tool with no output schema, the description covers the essential mental model: precondition, resulting status, and how to observe the async outcome. It leaves the failure/retry behavior unaddressed, which is the main remaining gap.

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% with only two parameters, both well documented in the schema ('Invoice UUID to submit to ANAF', company override using active company). The description adds no parameter-level meaning beyond the schema, 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?

The description opens with a specific verb+resource+target ('Submit an issued invoice to the ANAF e-Factura system'), which separates it from invoices_validate, invoices_issue, and invoices_efactura_message. It stops short of explicitly naming those siblings, so an agent must still infer the boundary with einvoice_submit and invoices_validate.

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?

It states the precondition clearly ('must be in "issued" status') and gives explicit follow-up routing: poll invoices_get or use invoices_events for the validation result. It does not tell the agent what to do if the invoice is in another status or when to prefer this over einvoice_submit/invoices_validate.

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