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

Annotations already signal read-only, idempotent, non-destructive behavior, and the description adds substantial context beyond that: the snapshot/sync anchoring semantics, credit-specific BALANCE_FETCH_ERROR and BALANCE_CONSENT_ERROR cases, degraded fallback rows, warning fields, and the exact response envelope. This is rich, non-obvious behavior that directly affects how the agent should interpret results. No contradiction with annotations.

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?

Despite being long, every sentence carries operational meaning: snapshot nature, synchronization caveat, fallback to force_sync, credit error modes, degraded rows, and response shape. It is front-loaded with the core result and then layers necessary caveats. There is no filler or tautological prose.

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 tool with one parameter and no output schema, the description is unusually complete. It covers invocation semantics, constraints, failure modes, degraded behavior, warnings, and the response envelope. An agent has enough information to call the tool correctly and interpret every plausible outcome.

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 schema provides only the bare type (array of strings) with no per-field description, so the description carries the burden. It usefully adds 'Pass account_ids as an array (1–50)', giving the cardinality bound and reiterating the array shape. It could specify more about the ID format or provenance, but it compensates reasonably for 0% schema coverage.

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?

States a precise verb-resource pair ('Returns the latest available balance per account id') plus the REST endpoint, and clearly differentiates the snapshot nature of the balance from a live read. It also names sibling tools (openfinance_list_transactions, openfinance_force_sync) in context, so an agent can tell what this tool is and is not.

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?

The description explicitly tells the agent when to use openfinance_force_sync and then re-read if the balance seems stale or disagrees with transaction sums. It also explains when degraded rows appear instead of errors. It does not explicitly contrast with openfinance_get_accounts_detail or openfinance_list_accounts, but the operational guidance is clear and actionable.

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