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

Annotations already carry readOnlyHint/idempotentHint/destructiveHint, and the description adds substantial behavior beyond them: the freshness caveat (snapshot anchored to last upstream sync, not a live read), the updateDateTime semantics, structured warnings instead of throws for CREDIT accounts (BALANCE_FETCH_ERROR, BALANCE_CONSENT_ERROR), and row degradation with realtime:false on upstream 5xx. Nothing 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?

Front-loaded with purpose, then logically ordered caveats: freshness semantics, recovery path, parameter format, credit-card error modes, degradation behavior, response shape. It is long, but each sentence earns its place given the error complexity; minor redundancy exists in the two 'instead of throwing/error' clauses.

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?

With no output schema, the description supplies the response shape '{ results: [...], errors: [{ id, status, message }] }' plus the row fields that matter (realtime, updatedAt, warning), covering param constraints, error conditions, and degradation. The one gap is that successful result rows are not fully enumerated (e.g., balance amount/currency field names), so an agent parsing results has to infer the value field.

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 must compensate — and it does with 'Pass account_ids as an array (1–50)', adding the size bound and confirming the expected format. It does not enumerate the account id string format, but that is largely self-evident from the parameter name and sibling tool context.

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 states a specific verb and resource — 'Returns the latest available balance per account id (GET /accounts/:id/balance)' — naming the exact endpoint. This is unambiguous against siblings like openfinance_list_accounts (listing) or openfinance_get_credit_card_bill (credit bills), so an agent can distinguish it without opening the schema.

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 explicitly names openfinance_force_sync as the alternative and gives the selecting condition: 'If a movement that just happened is not reflected yet, or the balance disagrees with the sum of openfinance_list_transactions, run openfinance_force_sync to pull fresh data and then re-read.' The recovery sequence is spelled out rather than left to inference.

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