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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower, but the description adds substantial behavioral context: connector-dependent balance semantics, stale `bankData` fields after connection creation, provider_incident blocks indicating unreliable values, and identity_notice deduplication guidance. These go well beyond the annotations and materially change how the tool's results should be interpreted.

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 contract in the first sentence, and each subsequent paragraph covers a distinct operational warning worthy of inclusion. It is not maximally concise, and a tighter structure would improve scannability, but no sentence is purely filler.

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 read-only list tool with no output schema and a complex multi-connector domain, the description covers the return fields, aggregation behavior across connections, bulk mode, provider incidents, identity notices, and how to handle ambiguous balance values. An agent has enough context to call the tool correctly and interpret responses appropriately.

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 input schema provides only property names and an enum, with 0% description coverage, so the description must compensate. It explains `item` thoroughly (omit for all banks, pass for a single bank), the BANK/CREDIT type values, and the bulk `item_ids` parameter. However, the singular `item_id` parameter is not explicitly explained, leaving a small 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 states a specific verb and resource: it returns accounts for a bank connection, covering BANK and CREDIT types with named fields such as balance, number, type, subtype, bankData, and creditData. It also distinguishes itself from sibling tools like openfinance_list_credit_card_bills by clarifying that bills come from that tool rather than this one. The all-banks vs single-bank scope is explicitly described.

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 when-to-use instructions: omit `item` to list accounts across all linked banks when the user asks for 'my accounts/cards' without naming a bank, and pass `item` to target a single bank. It also names the alternative openfinance_list_credit_card_bills for standardized open-bill and closed-bill amounts, and warns against treating `balance` as a monthly bill. Even reconciliation via openfinance_force_sync is mentioned.

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