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

Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds substantial behavioral detail beyond that: the balance is a snapshot anchored to the last upstream sync, not a live read; credit accounts may return specific Pluggy errors; non-Open Finance connectors or upstream 5xx responses degrade to a last-synced balance with realtime:false and a warning instead of throwing. These details are not present in the annotations and materially affect how an agent interprets 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 densely informative, and each sentence earns its place. It opens with the core behavior, then logically covers freshness caveats, error modes, degradation, and response shape. No fluff or repetition; every detail supports correct invocation and interpretation.

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?

Even though there is no output schema, the description specifies the response envelope ({ results, errors }) and the key row fields (updateDateTime/updatedAt, realtime, warning) plus error and degradation behaviors. An agent has enough information to invoke the tool, anticipate failures, and correctly interpret the returned data.

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 only defines account_ids as an array of strings with zero description, so the description carries the entire semantic burden. It adds the crucial constraint that account_ids must be an array of 1–50 items, which directly supplements the bare schema. It does not provide an example or explain how to obtain account IDs, but for a single-parameter tool this is reasonable compensation.

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 clearly states it returns the latest available balance per account id and directly identifies the underlying endpoint (GET /accounts/:id/balance). It also differentiates itself from related tools by referencing openfinance_force_sync and openfinance_list_transactions in the data-freshness flow. There is no ambiguity about the operation or resource.

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 conditional guidance: if a recent movement is not reflected or the balance disagrees with transactions, run openfinance_force_sync and re-read. It also explains when errors occur and how to recover from consent issues. It does not explicitly state 'use this when you need the latest balance' in a standalone sentence, but the snapshot caveat and sync suggestions make the intended context clear.

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