Connect a bank

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

With no annotations provided, the description carries the full behavioral disclosure burden. It explains the external-browser redirect flow, the read-only nature of the consent, the callback to the server, the appearance of accounts afterward, and the 180-day expiry. This is comprehensive and leaves no major behavioral surprises.

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 sentences deliver the core action, the multi-step flow, and the consent lifetime with no filler. The main purpose is front-loaded in the first sentence, and every following sentence earns its place.

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, the description gives the essential return semantics (a URL), the required follow-up action (open in browser and approve), the post-approval effect (redirect and accounts in list_accounts), and the consent duration. Nothing an agent needs to correctly invoke and understand the outcome is missing.

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 description adds no parameter-specific meaning, while the schema already covers bank (exact name from list_banks) and country (ISO code, default DK). The customer_type parameter is documented only through its enum values and default. With 67% schema coverage, the description does not need to compensate heavily, but it also contributes nothing beyond the schema.

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 specific verb and resource: 'Start linking a bank.' It then explains the exact mechanism (returns a URL for browser login/approval) and clearly differentiates from siblings like consent_status (checking status) and disconnect_bank (ending a consent). The role of the tool is unambiguous.

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 provides clear contextual guidance: it is the initiation step, and after approval the accounts will appear in list_accounts. This strongly implies when to use it relative to other tools. However, it does not explicitly name alternatives or state when not to use it, so it stops short of a 5.

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