Find Duplicate Bank Accounts

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

Annotations already cover read-only, idempotent, and non-destructive hints. The description adds genuine behavioral context beyond those: it returns candidate pairs, matched/unmatched transaction counts, date ranges, sample matched pairs, and an AI same-account verdict. It clearly states the tool does not mutate anything. Minor gap: no mention of possible latency or AI-based computation time, but this is not critical.

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 every sentence earns its place: it explains the duplicate-account scenario, the underlying user situation, what the tool returns, when to use it, and which sibling tool to use instead. Information is front-loaded with the core purpose first, and the read-only note is placed near the end without burying critical facts.

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 zero-parameter, read-only detection tool with no output schema, the description fully fills the gaps. It explains the return payload, the triggering user phrases, the domain problem (double-counted cash/P&L), and the read-only nature with a pointer to the merge sibling. Nothing an agent needs to invoke and interpret the result is missing.

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 has zero parameters and 100% coverage, so there is nothing to document. Baseline for zero parameters is 4, and the description compensates by explaining what the tool analyzes and what it returns, making the lack of parameters feel intentional rather than an omission.

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 a specific verb and resource: 'Find manual bank accounts that look like the same real-world account as a live bank feed...' This clearly distinguishes the tool from siblings like get_bank_accounts or get_reconciliation_status by naming the duplicate-account detection scenario rather than a generic listing operation.

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?

Explicit usage triggers are given: when a user reports wrong cash/balance after linking a bank, mentions a duplicate account, or asks about an inflated P&L. It also explicitly contrasts with the sibling alternative merge_bank_accounts, stating this tool is read-only and that merging is done separately.

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