aziel-runtime

ChainLock recall

chainlock_recall

Read-onlyIdempotent

Retrieve stamped facts from the local vault at depth 0-5, with optional chain and query filters. Returns grounded fact records or refuses when no stamped fact exists.

Instructions

Grounded ChainLock recall at depth 0–5 (id+h+fh facts or refuse=no-stamp). Stamped vault facts — not Bayesian rank and not tip-only. Use this when you need stamped facts from the local vault, not a Bayesian ranking. Do not use it for adaptive memory ranking or reading only the live tip; use memory_recall or chainlock_tip instead. Depth above 5 is clipped to 5. refuse=no-stamp when empty — do not invent a fact. Append-only; there is no chainlock_delete. Omit depth to use 1 (not 0). 0 = tip only; 5 = full chain / genesis budget. Omit c/chain to scan session+acts+recall+learn (not the whole roster). q/query is a case-insensitive subject/fact substring; empty q does not invent cards. Returns grounded facts (id, h, fh) or refuse=no-stamp.

Input Schema

TableJSON Schema

Name	Required	Description
`c`	No	Optional chain name. One of genesis, identity, ssh, session, acts, evidence, recall, mesh, library, learn. Alias: chain. Omit both to scan session, acts, recall, and learn — not the full roster.
`q`	No	Optional case-insensitive substring over subject/fact. Alias: query. Empty does not invent matches.
`chain`	No	Alias of c. Omit both to scan session, acts, recall, and learn — not the full roster.
`depth`	No	Optional recall depth. Omit for 1. 0 = tip only; 5 = genesis/budget maximum. Values outside 0–5 are clipped. Alias: d.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	FragGate or fabric code when present: FG-OK, FG-HALLUC-TOOL, FG-STUB, FG-LOCAL-ONLY, FG-UNKNOWN-OP, FG-GATE-REFUSE, FG-LAMB-REFUSE, or a module refuse such as MESH-* / AKM-*.
`door`	No	Door name. The public door is fraggate.
`ran_in`	No	Execution locale (for example aziel-runtime) when present.
`result`	No	FragGate body: ok, code, door, slug, op, engine_digest, ran_in, provenance, refusal, limitations, receipt, plus the engine result. Unknown names refuse FG-HALLUC-TOOL; stubs refuse FG-STUB.
`status`	No	HTTP-like status when present on wrappers (200 ok; 400+ error / refuse).
`display`	No	Human-facing envelope. Show display.action, title, and summary, then take the next input. Never echo raw tool names.
`receipt`	No	Optional receipt, ledger tip, or TemporalLock/ForgeReceipts exit when the door stamped one.
`refusal`	No	Explicit refuse object, code, or message when the door or engine refused.
`engine_op`	No	Resolved engine op when present (often inside result).
`ledger_tip`	No	Ask/refuse ledger tip when the door stamped one.
`provenance`	No	Provenance / input packet when the pipeline attached one.
`session_id`	No	Raw session id when session plumbing was used. Hidden unless the user asked for the chain.
`engine_slug`	No	Resolved engine slug when present (often inside result).
`limitations`	No	Capability limitations or Remain-OFF notes when present.
`engine_digest`	No	64-hex engine_digest when a true in-process engine ran (often inside result).

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv2.0.9Sep 29, 2026

changedOutput schema / description

Previous value: -"Display envelope shown to the user (display.title / display.summary) plus the machine result. Extra engine fields may appear."New value: +"Display envelope shown to the user (display.action / display.title / display.summary) plus the machine result. Extra engine fields may appear. Do not echo raw tool names."

changedOutput schema / properties / display / description

Previous value: -"Human-facing envelope. Show title and summary, then take the next input."New value: +"Human-facing envelope. Show display.action, title, and summary, then take the next input. Never echo raw tool names."

addedOutput schema / properties / display / properties / action

Added value: +{
+  "description": "Human-visible run frame. Always \"Run aziel runtime\". Product verb titles stay on title. Not a tool name.",
+  "type": "string"
+}

addedOutput schema / properties / display / properties / image

Added value: +{
+  "additionalProperties": true,
+  "description": "Present only when a real production included png_b64, jpeg_b64 (or the same byte family), or a cited http(s) image URL. No invented thumbs. Omitted on dry_run. reviewed is true only when executed production bytes are attached; a dry_run never mints reviewed.",
+  "properties": {
+    "data": {
+      "description": "Base64 image bytes copied from the production. Omitted for a URL-only cite. Never present on dry_run.",
+      "type": "string"
+    },
+    "mimeType": {
+      "description": "Sniffed image media type (image/png, image/jpeg, image/webp, or image/gif).",
+      "type": "string"
+    },
+    "reviewed": {
+      "description": "True only when data came from an executed production. False for a URL cite without bytes. Never true on dry_run.",
+      "type": "boolean"
+    },
+    "source": {
+      "description": "Production field the image was taken from (for example png_b64, jpeg_b64, or image_url).",
+      "type": "string"
+    },
+    "url": {
+      "description": "Cited http(s) image URL when the production named one. Not invented.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

changedOutput schema / properties / display / properties / title / description

Previous value: -"Short result title for the AI client."New value: +"Product verb title for the AI client. Not a raw tool name."

Changed5 schema fields changedv2.0.1Sep 14, 2026

changedInput schema / description

Previous value: -"All fields optional. depth is 0 (tip) through 5 (genesis/budget)."New value: +"All fields optional. Default depth is 1. Default chains are session, acts, recall, learn."

changedInput schema / properties / c / description

Previous value: -"Optional chain name to recall from. Omit to use the default recall path."New value: +"Optional chain name. One of genesis, identity, ssh, session, acts, evidence, recall, mesh, library, learn. Alias: chain. Omit both to scan session, acts, recall, and learn — not the full roster."

addedInput schema / properties / chain

Added value: +{
+  "description": "Alias of c. Omit both to scan session, acts, recall, and learn — not the full roster.",
+  "enum": [
+    "genesis",
+    "identity",
+    "ssh",
+    "session",
+    "acts",
+    "evidence",
+    "recall",
+    "mesh",
+    "library",
+    "learn"
+  ],
+  "type": "string"
+}

changedInput schema / properties / depth / description

Previous value: -"Optional recall depth. 0 = tip only; 5 = genesis/budget maximum. Values outside 0–5 are clipped."New value: +"Optional recall depth. Omit for 1. 0 = tip only; 5 = genesis/budget maximum. Values outside 0–5 are clipped. Alias: d."

changedInput schema / properties / q / description

Previous value: -"Optional query string to filter recalled cards. Does not invent matches."New value: +"Optional case-insensitive substring over subject/fact. Alias: query. Empty does not invent matches."

Addedv1.6.2Sep 12, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already mark readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description adds substantial behavioral detail: depth clipping above 5, default depth of 1, default chain set, refuse=no-stamp when empty, no fact invention, and append-only/no-delete semantics. This goes well beyond the structured annotations and does not contradict them.

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?

The description is dense and front-loaded, with the core purpose and exclusions near the beginning. It is somewhat longer than strictly necessary and repeats a couple of schema defaults (e.g., default chains), but every clause carries operational value and the structure is logical.

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 read-only recall tool with a rich output schema, the description is complete: it defines scope, defaults, edge behavior, alternatives, and return shape. An agent has everything needed to decide when to call it and what to expect.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds meaning not in the schema: depth values map to behavior ('0 = tip only; 5 = full chain / genesis budget'), out-of-range values are clipped, omitted c/chain scans a specific subset, and q is a case-insensitive substring with empty-q behavior. This significantly enhances the schema's parameter documentation.

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 description opens with a specific verb+resource ('Grounded ChainLock recall at depth 0–5') and specifies output shape ('id+h+fh facts or refuse=no-stamp'). It explicitly contrasts with 'Bayesian rank' and 'tip-only', differentiating it from siblings like memory_recall and chainlock_tip.

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 states exact use conditions ('Use this when you need stamped facts from the local vault') and exclusions ('Do not use it for adaptive memory ranking or reading only the live tip'), naming memory_recall and chainlock_tip as alternatives. It also clarifies defaults for depth and chains, leaving no ambiguity about invocation context.

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