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

Even though annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description adds substantial behavioral context: snapshot semantics tied to the last upstream sync, updateDateTime meaning, credit-account error modes (BALANCE_FETCH_ERROR, BALANCE_CONSENT_ERROR), graceful degradation with realtime:false and warnings, and the response envelope. This goes well beyond the 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?

The description is long but dense and well-structured: it front-loads the core purpose, then adds freshness caveats, failure modes, and response shape in a logical order. Every sentence adds necessary information that the schema and annotations do not provide.

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 behavioral complexity and the absence of an output schema, the description covers everything an agent needs to invoke and interpret results correctly: freshness limits, sync refresh path, per-error handling, degraded rows, and the exact response structure. No critical gap remains.

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?

Schema coverage is 0%, so the description must compensate. It does by stating that account_ids is passed as an array and explicitly limiting it to 1–50 items. It does not elaborate on the string format of the IDs, but the parameter name and endpoint usage 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 opens with a precise verb and resource—'Returns the latest available balance per account id'—and cites the exact endpoint. It distinguishes itself from sibling tools by clarifying freshness semantics and explicitly referencing openfinance_force_sync and openfinance_list_transactions for related operations.

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 gives clear guidance on when to call this tool versus alternatives: it notes that the balance is not a live read and directs the agent to run openfinance_force_sync when recent movements are missing or totals disagree with openfinance_list_transactions. It could more explicitly enumerate alternative tools for historical transactions or account details, but the core decision path is present.

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