Audit Account Reconciliation

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds substantial behavior beyond that: the per-mode request behavior ('one API request' without accountId vs. additional listing with accountId), an explicit 'Makes no changes' statement, and a genuinely useful interpretation note explaining that an old last_reconciled_at is not itself a problem if cleared_balance matches the bank. This equips the agent to interpret results, not just call safely.

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 every sentence earns its place: purpose and mode behavior are front-loaded, safety and workflow contrast follow, and the interpretation note closes with actionable diagnostic insight. It is logically ordered and dense without being padded, though slightly wordy compared to the tightest possible version.

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 two-mode diagnostic tool with an output schema already present, the description covers everything an agent needs: what the tool produces in each mode, that it makes no changes, when in the workflow to use it, and how to interpret ambiguous results. The reconciliation domain concepts (last-reconciled date, cleared balance, uncleared transactions) are all explained. Nothing critical is left to inference.

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% — both budgetId and accountId already have meaningful descriptions in the schema, so the baseline of 3 applies. The description reinforces the accountId semantics by explaining what 'inspect in detail' produces (uncleared/unapproved transactions since last reconciliation), but adds no fundamentally new parameter-level information beyond the 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 opens with a specific verb+resource ('Read-only reconciliation diagnosis') and precisely enumerates the two behavioral modes: account-level summary without accountId, and detailed transaction listing with accountId. It clearly differentiates itself from siblings like get_transactions (raw retrieval), audit_credit_card_payments (a different audit target), and review_unapproved by framing itself as the 'find what needs attention first' diagnosis step.

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 explicit when-to-use guidance ('use this to find what needs attention first') and states what the tool is NOT for ('actual reconciliation... happens in the YNAB UI'), preventing an agent from attempting to perform reconciliation through this tool. It does not name a specific sibling alternative, but the timing and workflow context ('compare against the bank statement', 'before actual reconciliation') are clear enough for an agent to route correctly.

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