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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false; the description goes well beyond them by disclosing snapshot staleness, credit-account error behavior (BALANCE_FETCH_ERROR / BALANCE_CONSENT_ERROR surfacing as a structured warning instead of throwing), and row degradation on upstream failure. No contradiction with 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 information-dense: endpoint, freshness caveat, remediation path, parameter format, and two distinct error behaviors all earn their place. It is front-loaded with the core purpose; a slight tightening of the error paragraphs is possible but nothing is 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 one-parameter read tool with strong annotations and no output schema, this covers everything an agent needs to invoke it correctly: parameter shape and size bound, response-row fields (updateDateTime/updatedAt, warning), error handling semantics, and the fresh-data alternative. The only omission is the full response payload shape, which no output schema exists to provide.

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, and it does: 'Pass account_ids as an array (1–50)' adds the cardinality constraint that the bare JSON schema omits (no minItems/maxItems). It does not explain the id format or where to source ids, though the sibling openfinance_list_accounts implies that.

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?

States a specific verb and resource: 'Returns the latest available balance per account id' with the exact endpoint (GET /accounts/:id/balance). The description further pins down its scope by characterizing the result as a sync-anchored snapshot rather than a live read, which clearly separates it from balance-related siblings.

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?

Gives explicit when-to-use guidance with a named alternative: if a recent movement is missing or the balance disagrees with the sum of openfinance_list_transactions, 'run openfinance_force_sync to pull fresh data and then re-read.' It also tells the agent when degraded error rows appear (upstream 5xx, non-Open Finance connector), leaving nothing to inference.

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