Refresh Accounts

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

Annotations already indicate this is not read-only, not idempotent, and not destructive. The description adds the key behavioral trait: the request is asynchronous ('do not wait for completion'). It also implies a side effect (institution refresh) that aligns with readOnlyHint=false. It doesn't disclose what the response contains or whether repeated calls are safe, but the async note is genuinely valuable beyond the 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?

One sentence, front-loaded with the action and scope, and the critical async behavior is appended concisely. Every word earns its place. No fluff or repetition of the title.

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?

For a zero-parameter tool with an output schema, the description is mostly complete: it says what it does and that it returns immediately. However, it doesn't mention what the response contains (e.g., a job ID or status), whether the refresh is per-institution or all institutions, or any side effects like rate limits or credential requirements. The output schema may cover return values, but the description could still add a note about how to check completion status.

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 tool has zero parameters, so there is no schema burden to compensate for. The description correctly implies the operation applies to all accounts with no configuration. A baseline of 4 is appropriate for a no-parameter tool; the description doesn't need to explain parameters that don't exist.

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 ('refresh') and resource ('institution refresh for all accounts'), and adds a non-obvious behavioral detail: it does not wait for completion. This distinguishes it from a synchronous refresh or a read-only listing tool like get_accounts. It loses one point because it doesn't explicitly name a sibling alternative or clarify what 'refresh' means in terms of data updates.

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 implies when to use it: when you want to trigger a refresh of all accounts and don't need to wait. However, it provides no explicit guidance on when not to use it, no mention of alternatives (e.g., get_accounts for reading current data, or a per-account refresh if one exists), and no caveats about rate limits or prerequisites like institution login. The context is clear enough for a basic call, but the guidance is thin.

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