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

The description thoroughly discloses behavior beyond annotations: it waits up to ~60s, polls until the item stops updating, returns error details, handles authentication failures via reconnect_url, and supports fire-and-forget via wait=false. It explains what statuses like needs_action and timed_out mean, providing rich context not present in 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?

The description is dense but well-organized, front-loading the core action and then covering usage, parameters, return values, and edge cases in a logical flow. Every sentence provides necessary information without filler, making it appropriately sized for the tool's complexity.

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?

The description is fully self-contained for a complex asynchronous mutation tool. It covers return structure (results/errors), field semantics (status, executionStatus, synced), authentication failure handling, timeout behavior, and provides next-step guidance (reconnect_url, openfinance_get_item_status). No output schema exists, so the description's thorough coverage is essential and complete.

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?

Even though the schema properties lack descriptions, the tool description fully explains both parameters: items accepts various selectors (item_id, connector_id, connector_name, custom_label) and can be omitted to sync all, while wait controls whether the call blocks or returns immediately. This adds semantic meaning far beyond the bare boolean/array types in the 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 tool forces a re-sync of bank connections and waits for completion. It distinguishes itself from siblings by explicitly noting 'WITHOUT disconnecting/reconnecting' and by naming openfinance_get_item_status for follow-up status checks.

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 explicit when-to-use context: 'Use this when a balance or transaction list looks stale'. It also gives usage variations (sync specific items vs. all, wait vs. fire-and-forget) and references the alternative openfinance_get_item_status for timeout handling.

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