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

The description adds substantial behavioral context beyond annotations: the default is non-writing, commit has the side effect of writing rows into the review queue, and each row is returned as ready/duplicate/invalid. It also communicates currency handling ('Amounts are read in the account's currency'), which is not visible in the structured 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 short and front-loaded, with no filler. It packs the main action, default behavior, commit behavior, and currency rule into four focused sentences. Every sentence adds information not already in the schema or annotations.

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 an output schema, the description is almost complete: it explains default behavior, commit flow, statuses, and the review queue. It does not specify how CSV rows are parsed into categories or how duplicates are detected, but the dry-run statuses and output schema make the tool safely usable initially.

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 describes csv, commit, and include_duplicates, but the description adds meaning: commit=true writes ready rows into the review queue, and the dry-run result contains every parsed row with a status. It also adds a currency interpretation for the csv data that the schema does not provide. Only account_id remains generic, though 'into one account' implies its purpose.

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 action and resource: 'Import a bank statement (CSV text) into one account.' It clearly distinguishes this tool from others like import_holdings by stating the resource type and scope. It also clarifies the two modes (dry-run vs commit), removing ambiguity about what the tool does.

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 explicitly states the default behavior ('Dry-run by default') and the condition for writing ('Pass commit=true to write the ready rows'), which tells an agent when previewing vs committing is appropriate. It does not name alternatives or exclusions such as when to use record_card_statement or import_holdings, so it stops short of full alternative-based guidance.

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