SAAX Protocol

Prepare a free, nonbinding signed proposal (preflight)

prepare_commitment

Prepares a free, NONBINDING signed proposal (preflight) for a desired SAAX capability. Validates capability, schema/version/digest, units, and the exact supported network/asset/rail/mode combination; returns a provider-signed proposal binding the request digest and normalized terms. Creates NO agreement, payment, custody deposit, service execution, resource reservation, or spending authority. A provider signature is NOT buyer acceptance. No preflight fee. Errors are typed DSC_* codes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "profileVersion": "<profileVersion>",
      "capability": "<capability>",
      "schema": "<schema>",
      "units": "<units>",
      "financialProfile": "<financialProfile>",
      "clientNonce": "<clientNonce>",
      "issuedAt": "<issuedAt>"
    },
    "name": "prepare_commitment"
  }
}

Input Schema

Name	Required	Description
`units`	Yes	Amount + unit
`schema`	Yes	Expected commitment schema
`issuedAt`	Yes	ISO-8601 client timestamp
`capability`	Yes	Desired capability
`clientNonce`	Yes	Caller-chosen nonce (echoed; replay idempotency)
`constraints`	No	Optional constraints
`profileVersion`	Yes	SAAX Discovery profile version (e.g. 1.0.0)
`intendedParties`	No	Intended parties
`financialProfile`	Yes	Financial axes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses zero side effects (no agreement, payment, custody deposit, execution, reservation, spending authority), that no fee is charged, that the returned provider signature carries no buyer obligation, and that failures surface as typed DSC_* error codes. That is precisely the safety and failure-mode context an agent needs before calling a signing operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then the validation behavior, then the negative-scope guarantees, then error semantics. The capitalized emphasis earns its place on safety-critical negations, and no sentence is redundant padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nine-parameter, heavily nested, mutation-adjacent tool with no annotations and no output schema, the description covers purpose, validation scope, absence of side effects, and error typing. The remaining gap is the concrete shape of the returned proposal (fields the agent will need downstream) and retry/idempotency guidance beyond the schema's note on clientNonce echo.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all nine parameters and the baseline would be 3. The description adds real semantic value by explaining that capability, schema/version/digest, units and the network/asset/rail/mode tuple are jointly validated and that the request digest is bound into the signed proposal — meaning not every accepted input yields a valid proposal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and artifact ('prepares ... signed proposal (preflight)') and immediately scopes it to a desired SAAX capability. The explicit negation list ('Creates NO agreement, payment, custody deposit, service execution, resource reservation, or spending authority') separates it cleanly from create_commitment and accept_commitment without requiring the sibling schemas to be opened.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use context: this is the free preflight step that validates capability, schema, units and financial axes before anything binding happens, and it states 'A provider signature is NOT buyer acceptance.' It does not name the follow-on sibling (create_commitment/accept_commitment) explicitly, so an agent must infer the sequence from the sibling list rather than being routed.

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

All SAAX Protocol tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?