listar_bancos

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

With no annotations provided, the description carries the full burden and does well: it explicitly states the API is read-only ('somente leitura'), describes the returned fields ('codigo', 'nome', 'tipo'), and discloses that the table is maintained by OMIE. It also reveals that the 'nome' filter is a server-side partial search, adding behavioral insight beyond the schema.

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 concise and front-loaded with the main purpose. Every sentence adds value: the resource being listed, usage guidance about filtering, the return field structure, and the read-only nature. There is no fluff or redundancy.

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?

Given the absence of an output schema and annotations, the description is fairly complete: it explains the tool's purpose, suggests filtering, lists the return fields, and clarifies read-only behavior. The main gap is the lack of explanation for the 'tipo' filter values and pagination parameters, but for a simple list tool this is a minor omission.

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?

The schema has 0% description coverage, so the description must compensate. It explains the 'nome' filter (partial search) and implies pagination ('em vez de paginar tudo'), but it does not explain the 'tipo' parameter or the exact semantics of 'pagina' and 'registros_por_pagina' beyond what their names and defaults suggest. This is a partial but not complete compensation.

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 clearly states the tool's action: 'Lista os bancos e instituições financeiras do OMIE' (lists banks and financial institutions), with a specific resource and context. It also distinguishes itself from sibling tools by explaining that this table is the source of bank codes for checking account registration.

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 clear usage guidance: because the base has over 1,200 institutions, users should filter by 'nome' rather than paginating through everything, and notes that OMIE performs a partial match. It does not explicitly name alternative tools (e.g., 'consultar_banco' for single lookups), so it misses the 'when-not-to-use' aspect.

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