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

Annotations already mark the tool read-only and idempotent, and the description adds substantial non-obvious behavior: account name is the legal issuer, not the brand; credit balance meaning is connector-dependent; balance_notice indicates a misleading zero; bankData fields can lag; provider_incident and identity_notice affect how values must be interpreted. None of this contradicts the 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 nearly every clause carries operational value and the core purpose is front-loaded. It loses a point because the caveats are written as dense prose paragraphs rather than being structured into scannable bullets or sections.

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 complex domain semantics, this description covers return fields, bank-name semantics, credit-balance pitfalls, incident/notice interpretation, dedupe rules, and parameter routing. Together with the annotations, it gives an agent everything needed to select and 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 description coverage is 0%, so the description must compensate. It explains `item` targeting and omitting behavior, `item_ids` for bulk execution, and the BANK/CREDIT distinction that maps to `type`. However, `item_id` is never explained, and the filtering effect of `type` is only implied through the return-value wording rather than stated explicitly.

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 first sentence clearly identifies the operation and resource: it returns accounts for a bank connection and enumerates BANK vs CREDIT plus the returned fields. The description further sharpens the purpose by distinguishing all-linked-banks mode from single-bank mode. This is specific, non-tautological, and distinct from sibling tools.

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?

It gives explicit routing guidance: 'OMIT item to list accounts across ALL linked banks... use this when the user asks for my accounts/cards without naming a bank' and 'Pass item to target a single bank.' It also redirects to openfinance_list_credit_card_bills for standardized bill amounts and warns not to tell the user a card has nothing to pay when balance_notice is present. This is strong when-to-use and alternative coverage.

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