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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes well beyond that by explaining sync anchoring, the meaning of updateDateTime/updatedAt, structured warnings instead of thrown errors, degradation when the provider is unavailable or the connector is not Open Finance, and consent-related failure modes.

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 longer than average, but it earns its length by covering freshness semantics, error conditions, and recovery steps. The core behavior is front-loaded, and the caveats are ordered by relevance. A slightly tighter sentence around the snapshot concept would improve it, but there is no filler.

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?

For a read-only tool with no output schema, the description does a solid job: it tells the agent what fields to expect (updateDateTime, updatedAt, warning), how rows behave on error, and how to recover. It does not describe the exact top-level response envelope, which would be helpful, but the operational context is strong enough for correct invocation.

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 input schema only gives the type (array of strings) with zero description coverage, so the description must carry the meaning. It states that account_ids should be passed as an array and constrains it to 1–50 items. It does not explicitly say the IDs come from a list_accounts call, but the tool name and sibling context make that reasonably inferable.

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 the exact operation (returns latest available balance per account id), identifies the endpoint, and immediately clarifies an important nuance: this is a snapshot from the last upstream sync, not a live read. That specificity distinguishes it from transaction-listing or account-detail siblings.

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 explicitly warns against treating the balance as a live read and gives a concrete decision path: if the balance is stale or disagrees with the sum of openfinance_list_transactions, run openfinance_force_sync and re-read. It also explains when credit accounts may return specific errors and how to recover, leaving no ambiguity about when this tool is appropriate.

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