propose_transactions

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

With no annotations provided, the description carries the full burden — and it exceeds it. It discloses that the tool never writes, returns JSON proposals, flags ambiguous rows with '!' that must not be silently promoted, preserves import-id metadata for deduplication, and instructs the agent to open accounts_to_open and show counts first. This is comprehensive side-effect and workflow disclosure far beyond a typical description.

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 section earns its place given 13 parameters and zero schema coverage. It is well-structured: scope first, non-writing behavior second, then the two required parameters, then a bolded post-processing checklist, then a compact overrides list. Key warnings ('THIS TOOL NEVER WRITES', 'NOT a path', 'Keep the ! flags') are front-loaded and emphasized.

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 13 parameters, no annotations, and 0% schema coverage, the description is complete. It covers the tool's purpose, its safety profile (read-only), the two required parameters, the meaning of every override, and the critical post-processing obligations. Though an output schema exists, the description still explains the essential result fields (mapping, ambiguities, accounts_to_open, counts) because they dictate agent action steps.

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 — and it does thoroughly. 'content' is explained as base64-encoded bytes or pasted text (not a path), 'account' gets a real-world example ('Assets:Checking'), and every override is listed with its value set: amount_shape ('signed' | 'debit_credit' | 'balance'), columns with a JSON example, date_format as strptime, decimal_separator ('.' or ','), sign ('normal' | 'inverted'), and opening_balance with its purpose. This fully compensates for the schema gap.

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 opening sentence states a specific verb and resource: 'Parse a bank statement (CSV or OFX/QFX) into PROPOSED transactions.' It differentiates itself from the sibling add_transactions by explicitly declaring 'THIS TOOL NEVER WRITES' and that it 'returns proposals as JSON.' An agent can immediately distinguish it from all 19 sibling tools.

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 names the alternative and the condition that selects it: 'add_transactions is still the only way anything reaches the book.' It also explains that content is 'NOT a path' because the hosted agent has no shared filesystem, clarifying an important usage constraint. The 'WHAT YOU MUST DO WITH THE RESULT' section further instructs the agent on the proper follow-up workflow.

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