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

Even though annotations already flag the tool as read-only and idempotent, the description adds essential behavioral context: the balance is a snapshot tied to the last upstream sync, not a live read. It also discloses failure/degradation modes, structured warnings, and the exact response envelope. This goes well beyond what annotations provide.

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 sentence carries distinct operational value: snapshot semantics, sync caveat, force-sync fallback, credit-account errors, degradation behavior, and response shape. It front-loads the core purpose and then details edge cases. The length is justified by the behavioral complexity it documents.

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 present, the description supplies the response envelope: `{ results: [...], errors: [{ id, status, message }] }`. It also covers error and degradation behavior, the sync-based staleness caveat, and the recovery path. For a single-parameter read-only tool, an agent has everything it needs to invoke it correctly and interpret the result.

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%, but the description compensates by explicitly specifying 'Pass `account_ids` as an array (1–50).' This adds the cardinality and multiplicity constraint that the raw schema does not convey. It does not explain the format of each account ID string, but the parameter name and tool context make that reasonably clear.

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 specific verb and resource: 'Returns the latest available balance per account id (GET /accounts/:id/balance).' It clearly identifies the operation, the entity (account balance), and the per-account granularity, which separates it from transaction or account-listing tools. The purpose is unambiguous and actionable.

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 practical guidance on when to use this tool versus openfinance_force_sync: if the balance is stale or disagrees with openfinance_list_transactions, run force_sync and then re-read. It also explains error scenarios for CREDIT accounts and when degradation occurs. It does not explicitly list exclusions or alternative balance sources, but the context is clear and actionable.

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