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

The description goes well beyond the annotations' read-only/idempotent hints by explaining that the balance is a snapshot anchored to the last upstream sync, not live. It discloses degradation behavior with realtime: false, credit-account-specific errors, consent-related failures, and the structured response shape including errors. This is substantial behavioral context that an agent needs to correctly interpret results.

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, with the core statement front-loaded and supporting details organized by scenario. Every sentence contributes to correct invocation or interpretation—snapshot semantics, error conditions, degradation, and response shape. It could be tightened slightly, but the length is justified by the tool's behavioral complexity.

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 correctly supplies the response envelope: { results: [...], errors: [{ id, status, message }] }. It also covers failure modes, consent/connection issues, and the synchronous force-sync fallback, making the tool actionable end-to-end. There are no obvious gaps in what an agent needs to call and interpret this 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?

With schema description coverage at 0%, the description carries the full burden for parameter meaning. It adds the crucial constraint that account_ids must be an array of 1–50 ids, which the bare schema does not express. The parameter name itself is self-explanatory, but the bound and array requirement are valuable additions.

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 the latest available balance per account id (GET /accounts/:id/balance).' It clearly distinguishes this from sibling tools like openfinance_list_accounts and openfinance_get_accounts_detail by focusing on balance retrieval. There is no ambiguity about the tool's core function.

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 provides clear guidance on when to re-run or fall back to another tool: if the balance disagrees with openfinance_list_transactions or seems stale, run openfinance_force_sync and then re-read. It also explains when errors degrade to warnings. It does not, however, explicitly state alternatives for use cases like getting account details or historical balances, so it stops short of a full when-not-to-use matrix.

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