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

The description discloses polling behavior up to ~60s, the return shape ({results, errors}), the meaning of status fields (synced, needs_action, timed_out), and the reconnect_url flow. It adds significant context beyond the sparse annotations (readOnlyHint=false, etc.), including that re-authentication needs user interaction. No contradiction with annotations; it clarifies the non-destructive nature.

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 every sentence adds value: it states the core action first, then use case, parameter syntax, return semantics, and error handling. There is no redundancy; it is front-loaded with the most critical information and structured logically. Despite length, it is the minimal complete explanation for such a complex tool.

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 no output schema and minimal annotations, the description carries all the burden and succeeds: it covers purpose, use cases, parameters, return values, edge cases (needs_action, timed_out), and follow-up actions. It is complete enough for an agent to select and invoke the tool correctly, including knowing when to use wait:false and how to interpret results.

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 coverage is 0%, but the description fully explains both parameters: items as an array of selectors with concrete examples (item_id, connector_id, connector_name, custom_label), and wait as a boolean with behavioral implications. It also explains omission of items means all linked banks, providing more than the schema could.

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 precise action: 'Forces the bank to re-sync one or more connections NOW and WAITS for it to finish'. It specifies the resource (connections), the operation (re-sync), and differentiates from siblings by mentioning 'WITHOUT disconnecting/reconnecting' and referencing openfinance_get_item_status for timeout. This clearly distinguishes it from other finance tools.

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 guidance: 'Use this when a balance or transaction list looks stale' and contrasts with disconnecting/reconnecting. It also explains when to set wait:false for fire-and-forget and when to re-check with openfinance_get_item_status. It says OMIT items to sync ALL linked banks, providing clear selection rules.

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