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

Despite annotations already declaring readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the description adds substantial behavioral nuance: the snapshot freshness semantics, credit-account error variants, degradation behavior with warnings instead of throwing, and the response shape. This goes well beyond what annotations provide and contains no contradiction.

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 dense and front-loaded with the core behavior and endpoint. Every sentence adds operational value, especially around error handling and freshness. It loses a point for being a wall of text that could benefit from light formatting or shorter sentences, but it is not padded.

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 compensates by stating the response shape explicitly: '{ results: [...], errors: [{ id, status, message }] }'. It also covers error cases, degradation, consent failures, and the relationship to force_sync, making the tool safe and actionable for an agent.

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?

The input schema provides only param name and type with no description coverage, so the description carries the burden. It adds the key constraint that account_ids must be an array of 1–50 and clarifies it relates to per-account balances. It could be slightly stronger by pointing to openfinance_list_accounts as the source for IDs, but the parameter meaning is sufficiently conveyed.

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' and identifies the exact endpoint GET /accounts/:id/balance. It clearly separates this from transaction listing and other Open Finance tools by focusing on balance snapshots per account.

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 explicit when-to-use guidance: it explains that this is a snapshot tied to the last sync, and tells the agent to run openfinance_force_sync and re-read if the balance is stale or disagrees with openfinance_list_transactions. It also constrains account_ids to an array of 1–50, which is concrete invocation guidance.

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