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

Annotations indicate non-readonly, non-destructive. The description adds: waits up to ~60s, polls, returns detailed status (executionStatus, lastUpdatedAt, synced). It explains needs_action with reconnect_url and timed_out behavior, and confirms no disconnect/reconnect. No contradictions.

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 front-loaded with the key action and use case. It structures parameter details, return values, and edge cases logically. Slightly verbose around needs_action but remains efficient and well-organized.

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?

Covers use case, parameter options, return format (results, errors with status fields), error states (needs_action, timed_out), and follow-up actions. Despite no output schema, the description provides adequate detail for correct invocation and handling.

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?

Schema has 0% description coverage. The description compensates fully: explains items accepts various selectors (item_id, connector_id, etc.) and that omitting it syncs all. Describes wait as boolean for synchronous vs. fire-and-forget. Adds meaningful context beyond schema.

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 verb 'forces re-sync' and the resource 'connections'. It specifies synchronous waiting and contrasts with sibling tools like openfinance_get_item_status. The purpose is unambiguous and distinct.

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?

Explicit when-to-use guidance: 'when a balance or transaction list looks stale'. It explains when not to use (no disconnect needed) and provides alternatives for timeout cases (openfinance_get_item_status). Parameter wait: false for fire-and-forget is also clarified.

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