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

Beyond annotations (readOnly, idempotent, non-destructive), the description reveals snapshot semantics, the meaning of updateDateTime/updatedAt, structured warnings instead of thrown errors, and degradation behavior for 5xx or non-Open Finance connectors. This is substantial behavioral context not available from 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 every sentence delivers critical operational information: freshness caveat, comparison to transactions, sync trigger, error conditions, and degradation behavior. It is front-loaded with the core purpose and organized by importance without redundancy.

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?

Given there is no output schema, the description richly covers return semantics, error cases, and corrective actions. It tells the agent how to interpret rows, what triggers warning vs. error, and how to handle each failure mode, making the tool callable without missing key context.

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 0% schema description coverage, the description compensates by specifying that account_ids must be an array of 1–50 items. It adds the size constraint and clarifies the array holds account identifiers, though it does not detail error behavior for invalid IDs or non-string entries.

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 states a specific verb and resource: 'Returns the latest available balance per account id' with an explicit endpoint. It distinguishes itself from siblings by clarifying this is a snapshot anchored to the last upstream sync, not a live read, which separates it from transaction listing and sync tools.

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?

It gives explicit when-to-use guidance: if a balance is stale or disagrees with transactions, run openfinance_force_sync and re-read. It also explains handling of credit-specific errors by reconnecting the bank, which tells the agent what to do instead of failing.

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