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

Beyond the annotations (readOnly/idempotent/non-destructive), the description discloses the 14-day staleness threshold, that the reconnect_url is a BROWSER deep link requiring Plaid Link step-up auth, and critically that this tool only returns the link rather than performing the reconnection. That boundary is exactly the kind of behavioral context an agent needs to avoid misusing the result.

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 purpose and usage framing are front-loaded in the first two paragraphs, and the Returns block is dense but earns its space because there is no output schema. The verbose field enumeration is the only mild bloat.

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?

With no output schema, the description fully carries the burden of documenting the return payload — top-level keys, per-item fields (institution_name, last_synced_at, days_since_sync, is_stale, error state, per-account days_since_balance_update), affected_budgets, affects_forecast, and reconnect_url. Nothing an agent needs to interpret the result is missing.

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?

The tool takes zero parameters, so the baseline is 4; there is no parameter syntax for the description to clarify. It simply operates on all connections by default, which is consistent with the empty 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 names a specific verb+resource combination — a per-connection staleness report covering time since each linked bank last synced and which surfaces (balance, budget, forecast) a stale connection taints. This is unmistakably distinct from siblings like get_plaid_item, list_plaid_items, or sync_plaid_item, even without naming them.

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?

It anchors usage with 'Answers "is my data up to date?"' and explains what the results reveal about downstream figures. It also points to remedies (reconnect via link, archive a closed account, manual sync for a healthy-but-behind connection), though it does not name the corresponding sibling tools or state when this tool should be skipped.

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