start_consent

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

The description discloses key behavioral traits: it creates a consent resource at the bank, builds a FAPI-BR compliant authorization URL, requires the user to authorize in a browser, and returns a consent ID and URL. It also explains the request_url_elicitation behavior. This goes well beyond the minimal annotations and gives the agent a clear picture of side effects and dependencies.

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 well-structured with a summary, Args section, and Returns note. It is longer than average but every part carries useful information, such as the scope list and the explicit payment-consent distinction. No filler or redundant content appears.

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 complexity of a multi-step consent flow, the description provides a complete picture: how to invoke it, what the user must do, how to finish via complete_consent, and how it relates to payment consent. The presence of an output schema means detailed return types are not required in the description, and the high-level return description is sufficient.

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?

Even though schema description coverage is 0%, the description thoroughly explains every schema parameter: subject_id (CPF or internal ID), bank (participating bank), scopes (with explicit examples and exclusion of payments), and request_url_elicitation (with behavior and fallback). This compensates fully for the lack of schema descriptions.

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 purpose: 'Starts the Open Finance Brasil consent flow for a user at a bank.' It specifies the concrete actions (creating a consent resource, building a PAR+JAR authorization URL) and distinguishes itself from payment consent by saying this is not for 'pix'/payments. This makes it easy to differentiate from sibling tools like start_payment_consent and complete_consent.

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 usage guidance: it explains when to use the tool, what the user must do with the returned URL, and that the flow should be completed by calling complete_consent. It also explicitly warns that payment initiation uses a separate dedicated consent flow, steering the agent away from misuse.

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