Transactions: add transaction

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

Annotations already indicate idempotentHint=false and readOnlyHint=false, but the description adds critical specifics: calling twice creates duplicates, no duplicate detection, and no v1 endpoint to update/delete. It also clarifies that input must be an array (even a single record is an array of one). These details go well beyond 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 front-loaded with a warning about non-idempotency and then provides purpose and usage. It repeats 'Not idempotent' twice, which is slightly redundant, but the structure is otherwise efficient and organized (purpose, usage, precautions). It is not overly verbose and conveys all essential information.

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 tool's complexity (array input, multiple optional fields) and the presence of a detailed schema and output schema, the description covers all necessary context: when to use, how to avoid duplicates, input format, and the lack of update/delete. It is complete for an agent to invoke correctly without additional ambiguity.

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 coverage is 100% with detailed descriptions for each field, so the baseline is 3. The description adds a valuable nuance: 'A single record is an array of one,' clarifying that even a single transaction must be wrapped in an array. It also reinforces the account must be a payment account, though the schema already states that. This modest addition justifies a 4.

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 clearly states the tool adds transactions to a payment account of a customer, with a specific use case (importing bank transactions from CSV or cash book). It distinguishes itself from read-only siblings like transactions_list by focusing on creation and explicitly mentions it takes one or many transactions. The verb 'add' and resource 'transaction' are precise.

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?

It explicitly says to use this for importing transactions that no bank connection delivers, and advises checking transactions_list first for the date range to avoid duplicates. It also warns that there is no duplicate detection and no update/delete endpoint, guiding agents on when to call and what precautions to take. It doesn't explicitly name alternatives but gives clear context.

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