Read a deal's public state: protocol state (OPEN/COMMITTING/REVEALING/CERTIFIED/VOID/EXPIRED), who has committed/revealed, deadlines, result, and certificate_id once issued. Inputs of other parties are never exposed.
| Name | Required | Description | Default |
|---|---|---|---|
| deal_id | Yes | The deal id (d_...). | |
| credential | Yes | Your API key (initiator) or any party's invite token for this deal. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It explicitly discloses that inputs of other parties are never exposed, which is a key privacy guarantee, and notes that certificate_id appears only once issued. It also signals a read-only operation via 'Read', though it does not detail error behaviors or rate limits.
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 two sentences with no filler. It front-loads the action ('Read a deal's public state') and packs essential details about the contents and privacy behavior. Every phrase adds 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?
There is no output schema, so the description appropriately lists the return fields (state, parties, deadlines, result, certificate_id). It also mentions the privacy guarantee. It does not cover error scenarios, but for a simple read operation with two documented parameters, this is sufficiently complete.
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 input schema already provides 100% coverage of both parameters (deal_id and credential), so the description does not need to compensate. It adds minimal extra meaning about the parameters themselves, but it does clarify what the deal_id represents through the context of public state. Baseline 3 is appropriate.
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 uses a specific verb 'Read' with a clear resource: 'a deal's public state'. It enumerates the exact contents (protocol state, parties, deadlines, result, certificate_id) and differentiates from siblings like get_certificate or verify_certificate by focusing on the full public state rather than a specific artifact.
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 clearly implies the tool is for reading public deal state, but it does not explicitly state when to use it versus alternatives such as get_certificate or verify_certificate. No exclusionary guidance is provided, leaving the usage context inferred rather than stated.
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.
The core lifecycle tools (create_deal, commit_input, reveal_input, get_deal) are clearly distinct, and validate_input, compute_commitment_tool, and list_algorithms each serve unique steps. The certificate trio (get_certificate, get_public_certificate, verify_certificate) creates some ambiguity because two are fetch-style and one is verify-style, but their descriptions are strong enough to disambiguate in most contexts.
Most tools follow a consistent verb_noun snake_case pattern: create_deal, get_deal, commit_input, reveal_input, verify_certificate. The deviations are minor but noticeable: compute_commitment_tool appends an awkward '_tool' suffix, and get_entropy describes a domain-specific action rather than a clean action_object.
Twelve tools is well-scoped for a domain covering onboarding, algorithm discovery, deal creation, sealed commitment/reveal, entropy finalization, and certificate verification. Each tool maps to a distinct workflow step, and none feel redundant or purely decorative.
The main path from create_key and list_algorithms through validate, commit, reveal, get_entropy, and certificate verification is fully covered, and VOID/EXPIRED states handle abandoned deals. Minor gaps include no explicit cancel/abort tool and no clear representation of public versus parties-only deals in the create_deal description.