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

Annotations only give readOnlyHint=false and destructiveHint=false, but the description adds rich behavioral detail: PATCH method, polling up to ~60s, return structure with `synced` and `needs_action`, `reconnect_url` behavior, and that no slot is consumed. This aligns with annotations and provides critical context about side effects.

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?

Though dense, every sentence carries operational value: core action, return format, error states, timing, and alternative mode. The semi-colon structure and explicit commands ('Pass... OMIT... Set...') make it easy to scan despite length.

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?

No output schema exists, so the description covers return details (`{ results, errors }`), per-result fields, needs_action with reconnect_url, timed_out handling, and wait behavior. This is complete for a tool with polling and re-authentication complexity.

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%, so the description fully compensates. It explains `items` as an array of selectors (item_id, connector_id, connector_name, custom_label) and the special 'omit to sync ALL' case, plus `wait` as a boolean to toggle synchronous waiting vs fire-and-forget.

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' – a specific verb, resource, and behavior. It distinguishes from sibling tools like openfinance_get_item_status by describing the polling mechanism and explicitly framing this as the 'fresh data' tool.

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?

Provides explicit when-to-use guidance: 'Use this when a balance or transaction list looks stale'. It also explains alternatives and constraints: no disconnect/reconnect needed, use openfinance_get_item_status for re-checking timed_out cases, and wait:false for fire-and-forget.

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