propose_receipt_transaction

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

There are no annotations, so the description carries the full transparency burden. It discloses that the tool never writes, returns JSON, flags values below the confidence floor rather than returning them, reads the book's open directives, and validates account/currency issues early. This is exceptionally transparent for a mutation-adjacent tool.

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 appropriately dense for a 19-parameter tool with no annotations. It front-loads the core purpose and bolds the most important behaviors. A little phrasing is colorful rather than purely functional, but each sentence adds operational value.

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?

It covers the high-risk aspects: no writes, flagging behavior, receipt currency/account alignment, and the downstream approval flow. The output schema covers return shape. The main gap is lack of explicit instruction that the required receipt_sha256 comes from the prior stage_receipt step and slight ambiguity around line_items_json structure.

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 0%, so the description must compensate. It meaningfully explains the confidence floor, confidence fields, expense_account/paid_from_account, and exchange_rate semantics. However, it leaves a few non-obious params like receipt_sha256, line_items_json, and operating_currency without explicit explanation, so it is not fully complete.

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 and resource: 'Turn what you read off a staged receipt into a PROPOSED transaction.' It also explicitly differentiates itself from the write path by saying 'It NEVER writes' and pointing to add_transactions as the subsequent commit step, so an agent can distinguish it from siblings.

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 gives a clear workflow: supply the reading and per-field confidences, review flagged fields, then pass the returned beancount to add_transactions unchanged. It also states operational rules such as the confidence floor being raisable but never lowerable and exchange_rate being taken from the card statement, never invented.

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