Get real-time balances

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

The description adds critical behavioral context: it always hits the institution and is 'billable per call in production'. Since no annotations are provided, this is essential for agents to understand the cost implication and real-time nature, which is not evident from the schema.

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 a single, focused sentence that conveys the key purpose and a critical caveat (billable). It is front-loaded with the main action and differentiator, with no wasted words.

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 the simplicity of the tool (2 params, no output schema), the description covers the essential operational context: real-time nature, cost implications, and endpoint identity. It doesn't cover error cases or pagination, but with such a lean schema, this is sufficient.

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 has 100% coverage for both parameters, so the description does not need to add much. However, the description could clarify that item_id can be an access_token, but the schema already says 'or a raw access_token you already hold', so it adds no extra value.

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 the specific endpoint (/accounts/balance/get) and its unique role as the only endpoint that always fetches a fresh balance from the institution. This distinguishes it from siblings like plaid_accounts_get which likely returns cached balances.

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 notes the endpoint is 'the only endpoint that always hits the institution for a fresh balance', which implies when to use it (when fresh data is needed). However, it does not mention alternatives or when not to use it (e.g., when cached is acceptable).

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