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

Annotations already mark this as read-only and idempotent, but the description goes far beyond that by explaining connector-dependent balance meanings, balance_notice, stale bankData fields, provider_incident unreliable data, and identity_notice duplicates. These are precisely the behavioral caveats an agent needs to avoid misinforming users. No contradiction with annotations exists.

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 long but front-loaded with the core return value and bank/brand distinction before diving into caveats. Every major paragraph covers a distinct, decision-relevant edge case, though a little trimming could make the critical flow from normal usage to cautionary notes even clearer.

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 there is no output schema, the description does an excellent job of covering response fields, root vs. aggregate shapes, edge cases, and alternative-tool routing. It also warns against common misinterpretations such as treating CREDIT balance as the current bill or presenting stale provider-reported values as real. This is as complete as an agent needs to invoke the tool correctly.

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 coverage is 0%, so the description carries the full burden. It explains `item` omission vs. presence and the bulk `item_ids` behavior very well. However, the singular `item_id` parameter is not explicitly differentiated from `item`, and `type` is only implicitly covered through the BANK/CREDIT discussion rather than as a filter parameter.

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 clearly that it returns bank and credit accounts with their balances, types, and associated banking metadata. It also distinguishes itself from sibling tools by naming openfinance_list_credit_card_bills and explaining how it differs from that tool. The description makes the tool's scope immediately actionable.

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?

Provides explicit when-to-use guidance: omit `item` to list all banks, pass `item` to target a single bank, and use item_ids for bulk execution. It also tells the agent when NOT to use this tool's CREDIT balance and instead call openfinance_list_credit_card_bills for standardized bill data. This is exceptional routing guidance.

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