Skip to main content
Glama

AstraNL Coordination Protocol

commitment_attest

Issue a certificate recording the fact of an agreement only. AstraNL holds no money, guarantees no performance and is not a party. Submit only an agreement the parties have actually made and authorized you to record. A step can stand on confirmed references supplied in based_on. The connector sets created_by; it is not a caller field. The JSON request must be at most 25000 bytes. One party may record what was agreed and let the other confirm. The first response returns confirm_url with confirmation_capability once; keep it and give it to the other party only. They confirm or dispute on that page, or their agent calls commitment_confirm. Until answered or the 30-day offer expires, commitment_verify shows PENDING. Put price, date and extent of work as plain text in obligations or conditions. context is optional free metadata; context.data_quality set to test marks a rehearsal, excluded from real counts. Whoever holds the id or link can read the record.

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": {
      "parties": "<parties>",
      "obligations": "<obligations>"
    },
    "name": "commitment_attest"
  }
}

Input Schema

NameRequiredDescriptionDefault
contextNo
partiesYes
based_onNo
conditionsNo
obligationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses that the service is not a party and holds no money, that the connector sets created_by, a 25000-byte request cap, that confirm_url/confirmation_capability is returned only once and must be preserved, the 30-day expiry, the PENDING state, that context.data_quality=test excludes the record from real counts, and that anyone holding the id or link can read it. These are exactly the operational facts an agent cannot get from the annotations.

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

Conciseness4/5

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

Roughly 120 words, front-loaded with the core purpose and its limits, and nearly every sentence carries non-obvious information. The remaining flow is somewhat scattered, jumping from field guidance to byte limits to the confirmation workflow to access control, rather than grouping constraints and workflow together.

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

Completeness5/5

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

For a mutation tool with a nested schema and no output schema, the description covers what the call produces (confirm_url with a one-time capability), the lifecycle after creation (confirm/dispute/expiry, PENDING in commitment_verify), size limits, and access semantics. An agent has everything needed to call it correctly and to tell the user what to do with the response.

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?

With 0% schema description coverage, the description compensates well for most fields: it says to put price, date and extent of work as plain text in obligations or conditions, that based_on carries confirmed references, that context is optional free metadata with a data_quality=test convention, and that created_by is not a caller field. It never explicitly maps the required parties array (role/name pairs, 2–10 items) or the per-array limits, so one required parameter's structure is left to the schema alone.

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?

The first sentence states a precise verb and resource ('Issue a certificate recording the fact of an agreement') and immediately bounds the scope: 'only', 'holds no money, guarantees no performance and is not a party'. This separates it cleanly from the sibling commitment_confirm and commitment_verify, whose roles are also named later.

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

Usage Guidelines5/5

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

It gives an explicit precondition ('Submit only an agreement the parties have actually made and authorized you to record') and lays out the full workflow: record here, hand confirm_url to the counterparty, who then confirms via the page or commitment_confirm, with commitment_verify showing PENDING until answered or the 30-day offer expires. The when-to-use and the routing to alternatives are both explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources