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

Annotations already declare readOnlyHint and idempotentHint, so the description does not need to restate safety. Instead it adds valuable behavioral context: the balance is a sync-anchored snapshot, credit accounts can return BALANCE_FETCH_ERROR or BALANCE_CONSENT_ERROR, and upstream 5xx failures degrade to last-synced data with realtime:false and a warning. This goes well beyond the annotations without contradicting them.

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 every sentence earns its place: purpose, freshness caveat, recovery instruction, parameter format, credit-specific errors, and degraded-mode behavior. It is front-loaded with the core purpose and endpoint, then layers caveats logically without repetition or filler.

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 present, the description provides the response shape, error-row structure, warning behavior, degraded mode, and the distinction between synced snapshot and live data. For a read-only balance tool with one parameter, this is complete enough for an agent to select and invoke it 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?

The schema provides only a required array parameter with no description (0% coverage), so the description must carry the semantic burden. It does so by specifying 'Pass `account_ids` as an array (1–50),' making the array format and cardinality explicit, and by tying the parameter to account-level balance retrieval.

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 (GET /accounts/:id/balance).' It clearly distinguishes this from live reads and from sibling tools like openfinance_list_accounts or openfinance_list_transactions by emphasizing the snapshot nature and the exact endpoint.

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 explicitly tells the agent when data may be stale, when to compare with openfinance_list_transactions, and when to recover by running openfinance_force_sync before re-reading. It also explains degraded-response behavior and when errors appear as warnings instead of exceptions, giving clear operational guidance.

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