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

Annotations already establish the tool as read-only and idempotent, but the description adds essential behavioral detail: balance is snapshot anchored to last upstream sync, updateDateTime is not a live read, and certain failures produce structured warnings instead of throwing. It also names exact error codes and recovery actions, going far beyond the 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 dense but purposeful, front-loading the core action and endpoint before diving into caveats. Each sentence adds operational value: sync freshness, error handling, and degradation conditions. The sentence structure is somewhat long and run-on in places, which slightly hurts readability, but no sentence is wasted.

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 covers the essential return semantics (snapshot time, warning rows) and error paths. It also explains the interaction with force_sync and the consent error resolution. An agent has enough information to select and invoke the tool correctly, including how to interpret unexpected results.

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 schema merely says account_ids is an array of strings with no descriptions, so 0% schema coverage means the description must carry the load. It does, by specifying 'Pass account_ids as an array (1–50)', which adds type detail and a size constraint. It does not elaborate on what constitutes a valid account id, but for this simple parameter the guidance is adequate.

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?

Description clearly states the tool returns the latest available balance per account id and even cites the HTTP endpoint. The resource and action are unambiguous, and it naturally distinguishes itself from transaction-listing siblings by focusing on balance data.

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?

Explicitly explains when to prefer this snapshot vs. forcing a refresh: if movements are missing or balance disagrees with openfinance_list_transactions, run openfinance_force_sync and re-read. Also describes specific error cases for credit accounts and when to reconnect the bank, giving the agent clear decision criteria.

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