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

Discloses key behaviors beyond annotations: waits up to 60s, polls for completion, returns detailed response fields (status, executionStatus, lastUpdatedAt, synced, needs_action with reconnect_url), and timeout handling. Annotations only show readOnlyHint=false, so description fully compensates.

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 a single paragraph but well-structured: main action first, then usage, parameters, response fields, and edge cases. Every sentence adds value, though slightly verbose; could be broken into shorter sentences for readability.

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 tool's complexity (2 params, no output schema, many siblings), the description covers behavior, parameter semantics, response details, error modes (needs_action, timed_out), and alternatives. Fully equips an agent to use the tool correctly.

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 explains both parameters: wait as boolean for fire-and-forget, items as array of selectors (item_id, connector_id, connector_name, custom_label), and omitting items syncs all. This adds complete meaning beyond the raw 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 bank to re-sync connections and waits for completion. It uses specific verbs ('Forces', 'WAITS') and resources ('connections', 'items'), and distinguishes 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 states when to use (stale balance/transactions), when not to use (alternative for rechecking timed-out syncs), and how to use (omit items for all connections). Provides clear context for when to set 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.