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

Annotations already declare destructiveHint=true; the description adds real value beyond that by scoping the blast radius ('only pro forma invoices can be deleted') and stating irreversibility ('Cannot be undone'), plus the underlying Számla Agent action for traceability. It stops short of covering auth requirements, not-found behavior, or what a successful call returns.

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 tight sentences, zero padding, and the destructive verb is front-loaded in capitals. Each clause (identifier rule, scope limit, irreversibility, routing) carries distinct information.

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-param destructive tool with no output schema, the description covers the selector rule, the scope restriction, irreversibility, and the sibling to use instead. Only error/not-found semantics and confirmation of outcome are unaddressed, which is a minor gap given annotations already flag destructiveness.

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 100%, so the baseline is 3, but the description adds the mutual-exclusion constraint ('give exactly one') that the schema does not express — both properties are merely optional strings with no oneOf. It also labels order_number vs invoice_number as alternative identifiers, though it adds no format guidance beyond the schema's example.

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?

Specific verb (DELETES) plus specific resource (one pro forma invoice / díjbekérő) and it names the domain term in both languages. It explicitly separates itself from szamlazz_reverse_invoice, so an agent can distinguish it from the closest sibling 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?

States the alternative and the condition that selects it ('a real invoice is never touched, use szamlazz_reverse_invoice'), plus the mutual-exclusion rule for the two selectors ('give exactly one'). Both when-to-use and when-not-to-use are covered explicitly.

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