Skip to main content
Glama
DeltaX-Public

DeltaX Preflight

Official
by DeltaX-Public
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

preflight_hash_decision

Read-onlyIdempotent

Validates a Preflight v2 decision and returns its canonical SHA-256 decision hash so evidence producers can bind facts to the exact proposal they checked.

Instructions

Validate a Preflight v2 decision and return {decision_hash}, its canonical SHA-256 digest. Invalid decisions return a tool error, not a hash.

When to use

  • Before an evidence producer binds facts to the exact proposal it checked.

When NOT to use

  • Do not treat the hash as proof of facts, approval of an action, or a substitute for preflight_check when policy and evidence are ready.

Input Schema

NameRequiredDescriptionDefault
decisionYesPreflight v2 object with schema_version "2", decision_id, context, and 1-100 unique candidate IDs with payloads.

Output Schema

NameRequiredDescriptionDefault
decision_hashYesCanonical SHA-256 digest.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.4
    • addedInput schema / properties / decision / examples
      Added value: +[
+  {
+    "candidates": [
+      {
+        "id": "review",
+        "payload": {
+          "action": "review"
+        }
+      }
+    ],
+    "context": {},
+    "decision_id": "example-review",
+    "kind": "decision",
+    "schema_version": "2"
+  }
+]
  2. Changed1 schema field changedv0.1.3
    • addedInput schema / properties / decision / type
      Added value: +"object"
  3. Changed2 schema fields changedv0.1.2
    • changedInput schema / properties / decision / description
      Previous value: -"Preflight v2 decision JSON document."New value: +"Preflight v2 object with schema_version \"2\", decision_id, context, and 1-100 unique candidate IDs with payloads."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "decision_hash": {
+      "description": "Canonical SHA-256 digest.",
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    }
+  },
+  "required": [
+    "decision_hash"
+  ],
+  "type": "object"
+}
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: invalid decisions raise a tool error rather than returning a hash, and the hash is explicitly not proof of facts or approval. It does not say whether the hash is stable across formatting/key ordering, which is the one behavioral detail a caller binding facts would care about.

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?

Front-loaded with the verb, return value, and error semantics in two sentences, then cleanly sectioned guidance. The 'When NOT to use' bullet is dense and jargon-heavy, but it is not redundant filler.

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?

An output schema exists, so return values need no elaboration, and the description still names the returned field and its digest algorithm. Error behavior, scope limits, and the sibling handoff are all present; nothing an agent needs in order to call this correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100% and the single parameter carries an inline description plus a full example, so the schema does the heavy lifting. The description adds only the 'v2 decision' framing and nothing about the nested candidate/context structure. Baseline 3 applies.

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 (validate), a specific resource (a Preflight v2 decision), and the exact return shape ({decision_hash} = canonical SHA-256 digest). It also implicitly separates itself from siblings by naming preflight_check and by the 'hash_*' pairing with preflight_hash_policy.

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?

Has explicit 'When to use' and 'When NOT to use' sections, including a named alternative (preflight_check) and the condition under which that alternative applies. The one gap is that it never contrasts with preflight_hash_policy, but the decision-vs-policy split is legible from the resource names.

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

Deploy Server

Other Tools