Provider only. Hands off finished work for an IN_PROGRESS contract: a hash of the artifact plus a pointer (URL or webhook reference) to where it actually lives. Only the hash and pointer are stored, never the artifact itself.
| Name | Required | Description | Default |
|---|---|---|---|
| contract_id | Yes | ||
| delivery_hash | Yes | 64-character hex SHA-256 of the delivered artifact. | |
| delivery_pointer | Yes | URL or webhook reference to where the artifact lives. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a key storage behavior: 'Only the hash and pointer are stored, never the artifact itself' and the 'Provider only' restriction. However, it does not explain whether submission automatically transitions the contract state or what happens after submission, leaving some behavioral ambiguity.
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?
Two sentences efficiently deliver the role, action, target contract state, and a critical constraint. No unnecessary words or repetition; information is front-loaded.
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 description covers the core action and storage behavior, but it omits post-submission outcomes (e.g., whether the contract moves to a 'pending confirmation' state, especially given the existence of contract_confirm_delivery). It also does not mention return values or errors, leaving some operational context incomplete.
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 already describes delivery_hash and delivery_pointer explicitly, and the description reinforces that only these are stored. The contract_id parameter lacks a schema description and the description adds no context about it, so the description adds marginal value over the schema.
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 action ('Hands off finished work'), the actor ('Provider only'), and the target resource ('an IN_PROGRESS contract'). It distinguishes itself from sibling tools like contract_accept_delivery and contract_reject_delivery by focusing on submission of a hash and pointer.
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 specifies when to use the tool (only for IN_PROGRESS contracts) and who can use it (Provider only). It also clarifies what to provide and what not to provide (the actual artifact is not stored). While it doesn't explicitly name alternative tools, the sibling names give context and the role restriction helps avoid misuse.
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 is scoped to a distinct resource and action within its domain (budget, contract, deal, escrow, hiring, wallet, workroom, trust). There is no overlap between tools; even similar operations like contract_confirm_delivery and escrow_confirm_delivery are clearly differentiated by context. A model can reliably select the correct tool for a given task.
Tools follow a consistent pattern of domain prefix followed by verb_noun (e.g., budget_status, contract_submit_delivery, escrow_get_quote, wallet_set_autopay_threshold). The naming is uniform across all 42 tools, with no mixing of conventions like camelCase or inconsistent verb placement.
With 42 tools, the server is heavily overloaded. While the scope of an 'Agentic Financial OS' is broad, the high count makes it difficult for an agent to quickly navigate and select the right tool. Many tools could be consolidated (e.g., multiple get/list tools per domain, documentation tools like *how_it_works that could be merged). The count exceeds the recommended range and feels excessive.
The tool set covers the full lifecycle of financial operations: budget management, negotiation (deal_open/propose/accept/cancel), contract creation and delivery with verification, escrow with payment protection, hiring workflows, wallet operations, trust checks, and a marketplace for data/services. There are no obvious gaps; even edge cases like disputes and audit trails are addressed.