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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds substantial behavioral context: the snapshot nature tied to last upstream sync, the meaning of updateDateTime/updatedAt, the difference between freshest available and live data, the specific error variants, and the degradation behavior with realtime: false and warnings. This goes well beyond the structured 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?

Although the description is lengthy, every sentence carries meaningful operational information: endpoint, freshness semantics, retry guidance, error cases, degradation behavior, and response shape. It is front-loaded with the core purpose and then expands into necessary edge cases without 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, the description fully specifies the response shape and error structure. It also covers the main edge cases (credit consent errors, provider failures, stale sync, degraded rows) and how to recover. The description is complete for an agent to correctly invoke and interpret the result.

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 only defines account_ids as an array of strings, but the description adds crucial semantic constraints: the array must contain 1–50 account ids, and the parameter identifies which accounts to fetch balances for. This fully compensates for the 0% schema description coverage.

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 states a specific verb ('Returns'), a specific resource (balance per account id), and the exact endpoint (GET /accounts/:id/balance). It clearly distinguishes itself from sibling tools by noting how it relates to openfinance_list_transactions and openfinance_force_sync, making its purpose unambiguous.

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 explicitly tells the agent when to use it, when the data may be stale, and when to switch to openfinance_force_sync. It also explains the conditions under which errors or degraded rows appear, giving clear operational guidance beyond just a bare definition.

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