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

The annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description goes well beyond them by disclosing connector-dependent credit balances, stale/phantom `bankData` values that lag after connection, provider incidents that make values unreliable, and identity_notice deduplication rules. These are exactly the behavioral nuances an agent cannot infer from the schema or annotations.

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 organized into logical blocks: core return fields, bank vs legal-entity naming, item filtering, credit balance caveats, notices, and bulk support. Nearly every sentence adds needed operational context, though it is dense enough that a few points could be condensed without losing value.

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 no output schema and only bare parameter names, the description is highly complete: it explains what fields appear, how `bank` and `name` differ, how to aggregate across banks, how to handle connector-dependent credit balances, what `balance_notice` means, how to handle provider incidents, and how identity_notice affects deduplication. It leaves no critical gap for an agent to call 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?

With 0% schema description coverage, the description carries the full parameter burden and largely succeeds: it explains `item` vs omitting it, implies `type` via BANK/CREDIT account types, and introduces `item_ids` for bulk execution. However, the singular `item_id` input parameter is not explicitly distinguished from `item`; it only appears as a row tag in the response, leaving a small semantic gap.

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: returns BANK and CREDIT accounts for a bank connection, listing the exact fields returned. It also distinguishes itself from openfinance_list_credit_card_bills by clarifying which tool provides standardized bill amounts, so an agent can differentiate it from a key sibling.

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 conditional usage instructions: omit `item` to aggregate across all banks, pass `item` to target a single bank, and use openfinance_list_credit_card_bills for standardized open-bill/total-debt values. It also tells the agent not to rely on `balance` when `balance_notice` is present, which is concrete when-to-use-this-tool guidance.

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