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

Beyond the annotations already stating readOnly and idempotent, the description adds meaningful behavioral details: the default response returns only balances, `incluir_movimentos:true` changes the response to include the movements, `data_inicial/data_final` default to today, and the tool returns the current real balance rather than the fixed-date initial balance. It does not contradict the schema or annotations.

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 core is front-loaded: first the operation and resource, then the distinction from siblings, then the parameters. It is slightly long and repeats the idea of `incluir_movimentos` more than once, but each informative portion stays relevant, so the length does not hurt.

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 no parameter descriptions in the schema, the description is strong: it names the returned balance fields, explains how to add movements, and gives the date defaults. A minor unaddressed point is that all parameters are optional and the description incorporates a different identifier but does not say what happens if no account identifier is supplied.

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?

With 0% schema coverage, the description carries most of the parameter burden and does well: it explains `conta`, `nCodCC`, `cCodCCInt`, `data_inicial`, `data_final`, and `incluir_movimentos`, including date formats and default behavior. However, the schema property `account` is not described, so about one parameter remains undocumented in both the schema and description.

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?

A description is explicitly says 'EXTRATO BANCÁRIO and SALDO ATUAL de uma conta account (ListarExtrato)' and immediately distinguishes it from omie_list_checking_accounts, which only gives `saldo_inicial` in a fixed date. An agent can know exactly what resource and operation this tool represents and can tell it apart from siblings.

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 names the alternative when it is supposed to be used: use this tool with `incluir_movimentos:true` to match the bank statement to Omie entries, and use omie_list_checking_accounts when only the accounting starting balance is needed. That is an explicit when/when-not without relying on inference.

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