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

Beyond annotations (readOnly, idempotent, non-destructive), the description adds critical behavioral context: it may include a `provider_incident` block indicating that credit limits and balances could be unreliable. This alerts the agent to potential data quality issues, which is highly valuable for correct tool usage.

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 concise at four sentences, with key information front-loaded. The first sentence states the core purpose, the second explains the output shape, the third addresses the special `provider_incident` case, and the fourth provides a specific usage warning. No extraneous content.

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 that there is no output schema, the description adequately explains the return structure (full account objects with creditData, batch `results/errors`, and potential `provider_incident`). It covers the most important behavioral nuance. However, it does not detail the fields within an account object, which might be assumed from context.

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 coverage is 0%, but the description compensates by explaining `account_ids` as an array (1–50 elements). This adds meaning beyond the raw schema, specifying both the data type (array of strings) and the length constraint. However, it does not describe individual string format beyond being IDs.

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 full account objects including extended creditData per ID. It specifies the endpoint pattern and the required parameter `account_ids`, making the purpose unambiguous. While it doesn't explicitly distinguish from `openfinance_list_accounts`, the focus on extended data and batch retrieval by IDs implies a distinct use case.

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 important usage context: it notes the batch shape `{ results, errors }` and warns about the `provider_incident` block causing unreliable data when the provider has an OPEN incident. This helps the agent decide when to trust the data. However, it does not explicitly state when to use this tool over siblings like `list_accounts`.

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