aziel-runtime

Adaptive recall

memory_recall

Read-onlyIdempotent

Ranks verified belief cards into a capped list for recall queries. Use after ChainLock verification when you need ranked beliefs, not raw stamps or library search.

Instructions

Ranked adaptive recall after ChainLock verify (AKM-TRIAD-1.0). Belief list — not raw grounded stamps, not a public corpus cite, not one-id explain. Use this when you want a ranked belief list after verify, not raw grounded stamps. Do not use it for grounded ChainLock recall, library search, or explaining one memory_id; use chainlock_recall, library_lookup, or memory_get instead. Does not authorize action (authorizes_action=false). Do not treat posterior rank as fact (belief_is_not_truth). Failed ChainLock verify refuses CHAIN_VERIFY_FAIL and does not invent cards. Empty grounded recall bubbles refuse=no-stamp. Ranking is capped at 16 cards. Omit depth to rank at 5 (full budget), unlike chainlock_recall which defaults to 1. q/query is lexical rank text, not a SQL filter. Empty q still verify-then-ranks stored cards. use_case weights triad_fit; it is not a permission. Optional limit clips the already-capped list. Returns ranked cards after verify (count, facts, belief_is_not_truth, authorizes_action=false).

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No	Optional lexical rank query (subject/fact). Alias: query. Empty still runs verify-then-rank; it does not invent facts.
`depth`	No	Optional ChainLock recall depth after verify. Omit for 5 (full budget). 0 is tip-only ranking.
`limit`	No	Optional result cap. Hard ceiling is 16 (MEMORY_CONTEXT_CAP) even if a larger number is sent.
`use_case`	No	Optional use-case label that weights triad_fit in ranking. Not a permission and not a truth claim.

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	Adaptive recall body: ok, adaptive=true, verified, count, facts (ranked cards with score/retrieval), belief_is_not_truth, authorizes_action=false. Refuses CHAIN_VERIFY_FAIL or no-stamp.
`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."

Changed6 schema fields changedv2.0.1Sep 14, 2026

changedInput schema / description

Previous value: -"All fields optional. depth follows ChainLock 0–5."New value: +"All fields optional. Default depth is 5. Empty q still runs verify-then-rank and does not invent facts."

changedInput schema / properties / depth / description

Previous value: -"Optional recall depth 0–5 after ChainLock verify."New value: +"Optional ChainLock recall depth after verify. Omit for 5 (full budget). 0 is tip-only ranking."

addedInput schema / properties / limit

Added value: +{
+  "description": "Optional result cap. Hard ceiling is 16 (MEMORY_CONTEXT_CAP) even if a larger number is sent.",
+  "maximum": 16,
+  "minimum": 1,
+  "type": "number"
+}

changedInput schema / properties / q / description

Previous value: -"Optional query to rank against. Empty query still runs verify-then-rank; it does not invent facts."New value: +"Optional lexical rank query (subject/fact). Alias: query. Empty still runs verify-then-rank; it does not invent facts."

changedInput schema / properties / use_case / description

Previous value: -"Optional use-case label that weights ranking. Not a permission."New value: +"Optional use-case label that weights triad_fit in ranking. Not a permission and not a truth claim."

changedOutput schema / properties / result / description

Previous value: -"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."New value: +"Adaptive recall body: ok, adaptive=true, verified, count, facts (ranked cards with score/retrieval), belief_is_not_truth, authorizes_action=false. Refuses CHAIN_VERIFY_FAIL or no-stamp."

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?

Beyond the annotations (readOnlyHint, openWorldHint false, idempotentHint, destructiveHint false), the description surfaces critical behavior: authorizes_action=false, belief_is_not_truth, ChainLock verify failure behavior, refusal modes, ranking caps, and default depth. This is substantial behavioral context that annotations alone do not provide.

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. It is longer than average and repeats a couple of points (e.g., 'not raw grounded stamps' and empty-q behavior appear more than once), but nearly every sentence adds a meaningful distinction or safety caveat, so the redundancy is minor.

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?

Given this tool's complexity, the presence of an output schema, and the rich sibling set, the description is complete: it covers failure modes, default behavior, cap limits, permission semantics, and how it differs from related tools. An agent has enough information to decide when and how to call this tool correctly.

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?

Although the input schema already covers all parameters (100% coverage), the description adds important semantics beyond the schema: q is 'lexical rank text, not a SQL filter', empty q still triggers verify-then-rank, depth defaults to 5 unlike chainlock_recall's 1, limit clips the capped list, and use_case is explicitly not a permission.

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 and resource: 'Ranked adaptive recall after ChainLock verify'. It explicitly differentiates from siblings by stating it returns a belief list 'not raw grounded stamps, not a public corpus cite, not one-id explain' and names chainlock_recall, library_lookup, and memory_get as the alternatives for those cases.

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 explicit when-to-use guidance ('Use this when you want a ranked belief list after verify') and direct when-not-to-use guidance with named alternatives ('Do not use it for grounded ChainLock recall, library search, or explaining one memory_id; use chainlock_recall, library_lookup, or memory_get instead'). It even contrasts the default depth with chainlock_recall, leaving no ambiguity about selection.

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