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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds substantial behavioral context: the snapshot nature, the meaning of updateDateTime, credit-specific error handling, structured warnings instead of throws, and degraded responses when the upstream is unavailable. This goes well beyond what annotations or schema convey.

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 each sentence carries meaningful behavioral or error-handling information. It is front-loaded with the core purpose. The density is justified given the nuanced error modes, though it could be slightly more scannable with list separators.

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 and one parameter, the description compensates fully by specifying the response shape, error structure, degradation behavior, and edge cases. An agent has enough context to invoke the tool correctly and interpret its results, including unexpected warnings.

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 no descriptions. The description adds crucial meaning: 'Pass `account_ids` as an array (1–50)', clarifying both the expected type and the cardinality limit. It also implies each element is an account id, tying the parameter to the per-account response.

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' and gives the endpoint. It clearly distinguishes this tool from siblings like openfinance_list_accounts or openfinance_get_accounts_detail, which serve different purposes.

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 provides practical guidance on when to use it and what to do if data seems stale: call openfinance_force_sync and re-read. It also warns about consent errors and degraded fallbacks. It does not explicitly enumerate when to choose alternative tools, but it names the relevant sibling (openfinance_force_sync) and gives concrete trigger conditions.

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