aziel-runtime

Resolve a memory outcome

memory_resolve

Append a resolution outcome to an already-observed memory: graded 0–1 or UNKNOWN, without rewriting history. Requires memory_id or subject and confirmation.

Instructions

Append a memory_resolution outcome on an already-observed memory (AKM-TRIAD-1.0). UNKNOWN is distinct from MISS. Does not rewrite history. Use this when an observed memory_id or subject now has an outcome. Do not use it for first observation, calibration, or reading history; use memory_observe, memory_calibrate, or memory_get instead. Write: additive resolution stamp. Missing memory_id/subject refuses AKM-NO-MEMORY. Does not rewrite prior observations. No memory_update — this is the forward outcome path. Requires memory_id or a previously observed subject. outcome is optional [0,1]; omit for UNKNOWN. Mutation requires confirm=true (runtime gate) or dry_run=true (preview only, no write). confirm and dry_run stay optional on inputSchema.required. Returns resolution stamp with outcome or UNKNOWN.

Input Schema

TableJSON Schema

Name	Required	Description
`fact`	No	Fact text clipped to 160 characters. Required on observe. Hash-only cards refuse AKM-NO-FACT.
`confirm`	No	Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true (preview, no write).
`dry_run`	No	Optional preview flag. When true, return a would-mutate preview and do not write. Alternative to confirm=true. Does not mutate.
`outcome`	No	Optional graded outcome in [0, 1]. Omit (or pass UNKNOWN) for an UNKNOWN resolution — distinct from MISS.
`subject`	No	Optional subject key clipped to 80 characters. Used to find or create memory_id.
`use_case`	No	Optional use-case label for calibration / adaptive recall ranking. Not a truth claim.
`memory_id`	No	Optional existing memory id. Alternative to subject for resolve/calibrate/get.
`outcome_label`	No	Optional label (for example HIT, MISS, GRADED, UNKNOWN). UNKNOWN is a first-class state, not a miss.

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 title and summary, then take the next input.
`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.

Changed3 schema fields changedv2.0.2Sep 18, 2026

changedInput schema / description

Previous value: -"Requires memory_id or a previously observed subject. outcome may be omitted for UNKNOWN. Extra keys are accepted."New value: +"Requires memory_id or a previously observed subject. outcome may be omitted for UNKNOWN. Extra keys are accepted. Mutation requires confirm=true or dry_run=true."

addedInput schema / properties / confirm

Added value: +{
+  "description": "Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true (preview, no write).",
+  "type": "boolean"
+}

addedInput schema / properties / dry_run

Added value: +{
+  "description": "Optional preview flag. When true, return a would-mutate preview and do not write. Alternative to confirm=true. Does not mutate.",
+  "type": "boolean"
+}

Addedv1.6.2Sep 12, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The description goes well beyond the annotations (readOnlyHint=false, idempotentHint=false) by disclosing that it appends an additive resolution stamp, does not rewrite history, refuses with AKM-NO-MEMORY when memory_id/subject is missing, and treats dry_run as a no-write preview. This adds meaningful behavioral context that annotations alone do not convey.

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, then usage, then constraints. It has minor redundancy ('Does not rewrite history' and 'Does not rewrite prior observations' appear twice), but every part still contributes needed guidance; the repetition is a small cost against the strong structure.

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 the tool's complexity (8 parameters, mutation gate, error conditions, distinct UNKNOWN/MISS states), the description covers requirements, error responses, alternative tools, and preview behavior. An output schema exists, so return details are not necessary, and nothing essential is missing for an agent to invoke this correctly.

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 coverage is 100%, so the baseline is 3. The description adds valuable semantics beyond the schema: it clarifies the outcome omission means UNKNOWN, the mutual exclusivity/requirement of memory_id or subject, and the interplay between confirm and dry_run. It does not restate each parameter but provides higher-order usage meaning, justifying a 4.

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 states a specific verb ('Append') and resource ('memory_resolution outcome on an already-observed memory'), and explicitly distinguishes this tool from siblings by naming 'No memory_update — this is the forward outcome path.' It clearly differentiates from memory_observe, memory_calibrate, and memory_get within the same description.

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?

The description gives explicit when-to-use conditions ('Use this when an observed memory_id or subject now has an outcome') and when-not-to-use alternatives ('Do not use it for first observation, calibration, or reading history; use memory_observe, memory_calibrate, or memory_get instead'). It also explains the mutation gate with confirm=true or dry_run=true, leaving no ambiguity about prerequisites.

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