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

Annotations are minimal and do not contradict the description. The description adds important behavioral context beyond those annotations: reconciliation cannot be done after the fact as a separate call, and clearly warns that the only way to reconcile already-settled payments is to cancel and re-launch. This is genuinely useful and non-obvious behavior.

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 dense and front-loaded with the core purpose before moving into parameter details. Most sentences add genuinely useful information, especially the reconciliation warning and the helper reference to omie_list_checking_accounts. It is longer than average but justified by the nontrivial JSON structure it documents.

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 tool with no output schema and sparse annotations, the description covers the operation's intent, the required data payload, optional fields, date format, helper tool lookup, and the reconciliation-specific behavior. The main missing piece is documentation of the top-level 'account' parameter; otherwise the agent has enough context to invoke the tool 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 carries the burden. It does so well for the main 'data' parameter, explaining it is a JSON string with the settlement fields and their formats, including codigo_lancamento_omie vs codigo_lancamento_integracao, date format, and the optional observacao. However, the top-level 'account' parameter is not explained at all, leaving a small but real semantic gap.

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 precise verb and resource: 'Dá baixa (liquida/paga) uma conta a pagar', and ties it to the Omie operation 'LancarPagamento'. It clearly differentiates this from the reconciliation-only behavior and from related sibling flows by explaining that reconciliation happens through this settlement action, not through a separate call.

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 gives explicit when-to-use guidance: it is for settling payables and is the only way to reconcile a payment via the API. It also gives a concrete when-not/alternative path: for an already-settled payment, use omie_cancel_payment and re-launch the settlement with concatenation. This routes an agent to the right sibling without ambiguity.

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