review_transactions

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

It explicitly states 'never changes data' and 'Returns transaction IDs,' which are key behavioral traits. Given no annotations, this disclosure is valuable. However, it doesn't mention parameters' effects or potential costs.

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 a single clear sentence with no filler words, front-loading the main purpose.

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 no output schema and no annotations, the description covers the primary behavior and safety, but lacks parameter details and usage context, making it incomplete for a complex tool.

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 has no descriptions for its 4 parameters, and the description does not directly explain them. It indirectly maps 'period' to start/end dates and 'unusually large' to large_amount_rub, but duplicate_window_days remains unexplained. This partial compensation is not enough.

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 uses a specific verb (review) and clear resource (a period for duplicate, uncategorized, and unusually large transactions). It distinguishes itself from sibling mutation tools by explicitly stating it returns transaction IDs and never changes data.

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 implies its purpose (analyzing transactions) but does not explicitly state when to prefer it over list_transactions or suggest_category. It lacks exclusionary guidance like 'use this for review only, not for editing.'

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