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

Annotations only provide readOnly/idempotent/destructive hints. The description adds substantial behavioral context: connector-dependent `balance` meaning, `balance_notice` indicating a misleading zero, lagging `bankData` fields, `provider_incident` indicating unreliable values, and `identity_notice` requiring dedupe by account number. All of this goes well beyond the annotations and materially changes how an agent should interpret and present the response. 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 the length is earned by the density of real operational caveats. The main return value and key usage rule are front-loaded in the first sentence. Some organization into paragraphs or bullets would improve scannability, but no sentence appears redundant.

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 tool with no output schema and several subtle behavioral hazards, the description covers return fields, bank scoping, batch mode, credit-card balance pitfalls, provider incidents, data lag, and deduplication rules. An agent has enough context to call the tool correctly and interpret even edge-case responses without external assumptions.

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 for parameter meaning. It explains `item` (target a single bank), omitting `item` (list across all banks), and `item_ids` (batch). The `type` parameter is implied through BANK/CREDIT categories, though not explicitly tied to the parameter. `item_id` singular is not clearly differentiated from `item`, which prevents a perfect score.

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 precise verb and resource: 'Returns accounts for a bank connection: BANK ... and CREDIT ...' and enumerates the exact fields returned. It also distinguishes itself from openfinance_list_credit_card_bills at the point where a reader might confuse account balance semantics with bill amounts. This is a clear, specific purpose statement.

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 guidance on when to omit `item` versus pass it, when to use batch `item_ids`, and when to route to openfinance_list_credit_card_bills instead. It directly addresses the common user-facing query 'my accounts/cards' and specifies that the alternative tool should be used for standardized bill amounts. This is actionable routing guidance, not just a hint.

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