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

The annotations already establish readOnlyHint=true and destructiveHint=false, so the description does not need to repeat safety semantics. It adds useful behavior context on its own by explaining that the balances are book-side values and that discrepancies are what reconciliation resolves, which helps an agent understand the meaning of the data without implying any write or mutation behavior.

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 concise and front-loaded, with the core output in the first sentence and the reconciliation rationale in the second. The final 'Read-only.' is redundant with the readOnlyHint annotation, but it is a minor duplication rather than a structural problem.

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 simple one-parameter input, available output schema, and read-only annotations, the description is nearly complete for agent invocation. It could be slightly more explicit about which 'account tools' to compare against, but the included context explains the purpose and the data shape well enough.

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 description coverage is 100%: companyId is documented as a UUID value wrapper. The description does not add parameter-level detail, but with only one well-documented parameter this is acceptable and receives the baseline score for high 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?

The description states the exact resource (bank accounts and cards), the data produced (book balance and count of posted entries), and the reconciliation context, which clearly separates it from sibling accounting tools like accounting_get_balance_sheet or accounting_get_general_ledger. It lacks an explicit verb such as 'retrieve' or 'list', but the intent is unmistakable from the first sentence.

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 usage context: use this tool to see book balances per bank account/card and compare them against the bank's own balance from account tools. It does not explicitly list when not to use it or name specific alternative tools, but the reconciliation workflow guidance is strong enough for an agent to select it appropriately.

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