Submit up to 1000 directives atomically — all persist together or none do. Priced 10x a single write, regardless of batch size within the cap. Always paid — the free-trial allowance (see submit_directive) applies to single writes only, never to batches, even if you haven't used any free writes yet. Paid.
| Name | Required | Description | Default |
|---|---|---|---|
| nonce | Yes | ||
| signature | Yes | ||
| timestamp | Yes | ||
| directives | Yes | ||
| public_key | Yes | ||
| payment_header | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses atomicity ('all persist together or none do') and pricing (10x a single write). Since no annotations are provided, the description carries full behavioral burden. It lacks details on auth or error handling but covers key traits.
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 concise, with key information front-loaded. It contains minimal fluff, though pricing info is repeated. Still, every sentence serves a 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?
The tool has 6 parameters and no output schema, yet the description omits parameter details, return format, and error behavior. It covers high-level semantics but lacks completeness for practical invocation.
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%, and the description does not explain any parameters (e.g., nonce, signature, payment_header). Only 'directives' is implied via 'Submit up to 1000 directives'. This is insufficient for correct parameter usage.
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 'Submit up to 1000 directives atomically', specifying the verb 'submit', resource 'directives', and scope 'batch'. It distinguishes the tool from sibling 'submit_directive' by noting pricing and free-trial differences.
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?
Explicitly states when to use: 'Always paid — the free-trial allowance... applies to single writes only, never to batches'. This directly tells the agent not to use this tool for free-tier users, providing clear when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: account inquiries, financial reports, directive management, validation, key generation, and batch submission. No two tools overlap in functionality despite some being related reports.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., export_ledger, get_balance_sheet, list_accounts). The naming is predictable and clear throughout.
With 11 tools covering ledger management, reporting, validation, and key generation, the count is well-scoped for the server's purpose. Each tool justifies its existence without being too few or too many.
The tool set covers essential operations for a Beancount ledger: submission of directives (single and batch), listing of accounts and directives, generation of key financial reports, balance queries, validation, and key registration. No obvious gaps are present.