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

Thoroughly explains behavior: it is a write operation (no annotation contradiction), polls up to ~60s, returns timed_out and needs_action states with remedial actions. Details return fields including lastUpdatedAt, synced, reconnect_url. Annotations (readOnlyHint=false, destructiveHint=false) are consistent with the described behavior.

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 detailed but every sentence adds value. It is front-loaded with the primary action, then covers parameters, return values, and edge cases in a logical flow. No unnecessary words or redundancy.

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 the complexity of a sync operation with polling, multiple modes, and error states, and the absence of an output schema, the description is remarkably complete. It covers all return fields, error scenarios (needs_action, timed_out), and provides actionable links for user re-authentication.

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?

With 0% schema description coverage, the description fully compensates. It explains items as an array of selectors (item_id, connector_id, connector_name, custom_label) and that omitting it syncs all. It explains wait parameter semantics (true by default, false for fire-and-forget). No parameters left ambiguous.

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 bank to re-sync one or more connections and waits for completion. It uses specific verbs ('forces', 're-sync', 'polls') and identifies the resource ('connections'). It distinguishes itself from siblings like 'openfinance_get_item_status' for re-checking timed-out syncs.

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?

Explicitly tells when to use ('when a balance or transaction list looks stale') and when not (for timed-out cases, use 'openfinance_get_item_status'). Provides guidance on wait parameter (fire-and-forget vs. waiting) and error recovery (re-authenticate via reconnect_url for needs_action).

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