bank_link_start

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

With no annotations, the description carries the full burden and does well: it discloses that the tool returns a link rather than linking immediately, that consent persists up to 180 days, and the critical quirk that the final page may display an error yet its URL must still be captured. It stops short of describing failure modes, expiry/retry behavior, or any auth/quota constraints on the PSD2 flow.

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 short sentences, front-loaded with the identity of the tool, then the actionable procedure, then the consent lifetime. Every clause carries operational weight, including the parenthetical that prevents a common failure.

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?

No output schema exists, and the description fills that gap by stating the return value is a link and describing exactly what to do with it. For a four-optional-parameter initiation tool this is nearly complete; only error/expiry handling and the precondition that the account must not already be linked are absent.

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 description coverage is only 50%: 'bank' and 'psu_type' are documented in the schema, while 'days' and 'country' are not. The description partially compensates by tying consent duration to up to 180 days (the schema's maximum for 'days'), but 'country' is never explained and the exact-bank-name hint lives only in the schema, so much of the meaning still rests on structured fields.

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?

States a specific verb and resource ('Collega un conto corrente via Enable Banking (PSD2)') and explicitly names the sibling it hands off to ('passalo a bank_link_finish'), so an agent can separate it from bank_link_finish and bank_accounts without opening any schema.

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?

Gives a clear step-by-step usage path: open the returned link, authorize at the bank, copy the final page URL and pass it to bank_link_finish, including the counterintuitive case where the page shows an error. Lacks explicit when-not-to-use guidance (e.g. use bank_accounts for accounts already linked), but the forward workflow is unambiguous.

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