aziel-runtime

Explain a memory

memory_get

Read-onlyIdempotent

Instructions

Read one memory's stored explanation (node, history, or calibration: posterior, triad legs, effective N, Brier) — not a ranked list. Use this when you have a memory_id (or id) and need the stored explanation. Do not use it for ranked adaptive recall or appending an observation; use memory_recall or memory_observe instead. Missing both memory_id and id, or an unknown id, refuses AKM-NOT-FOUND — do not invent a node. authorizes_action stays false. There is no memory_delete; this is the read of the append-only node. Pass memory_id or id — one is enough; they are aliases, not two different records. Omit view for the default node slice. history returns events/resolutions; calibration returns posterior/triad/Brier. subject is not a lookup key here. Returns node, history, or calibration view (belief_is_not_truth).

Input Schema

TableJSON Schema

Name	Required	Description
`id`	No	Alias of memory_id. Do not send two different values.
`view`	No	Optional slice. Omit or get = stored node; history = events/resolutions; calibration = posterior, triad legs, effective N, Brier.
`memory_id`	No	Memory id to explain. Alternative to id. Missing both refuses AKM-NOT-FOUND.

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	Explain body: ok, memory_id, status, plus node or events or calibration fields. belief_is_not_truth. Refuses AKM-NOT-FOUND when the id is missing or unknown.
`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.

Changed5 schema fields changedv2.0.1Sep 14, 2026

changedInput schema / description

Previous value: -"Pass memory_id or id. view selects the explain slice."New value: +"Pass memory_id or id (aliases). Omit view for the node slice. Extra properties are rejected."

changedInput schema / properties / id / description

Previous value: -"Alias of memory_id."New value: +"Alias of memory_id. Do not send two different values."

changedInput schema / properties / memory_id / description

Previous value: -"Memory id to explain. Alternative to id."New value: +"Memory id to explain. Alternative to id. Missing both refuses AKM-NOT-FOUND."

changedInput schema / properties / view / description

Previous value: -"Optional view: get (default node), history, or calibration."New value: +"Optional slice. Omit or get = stored node; history = events/resolutions; calibration = posterior, triad legs, effective N, Brier."

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: +"Explain body: ok, memory_id, status, plus node or events or calibration fields. belief_is_not_truth. Refuses AKM-NOT-FOUND when the id is missing or unknown."

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?

Annotations already cover the read-only/idempotent/non-destructive profile, but the description adds substantial context beyond them: refusal code AKM-NOT-FOUND for missing/unknown ids, 'authorizes_action stays false', the append-only nature of the node, and the belief_is_not_truth return caveat. This is rich behavioral disclosure.

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 core action and scope, and sentences generally earn their place. However, the alias point ('Pass memory_id or id — one is enough; they are aliases') and the view semantics are each restated, adding some redundancy for a 3-parameter getter.

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 tool with full schema coverage and an output schema, the description is more than complete: it explains error behavior, aliasing, view semantics, and safety flags. Nothing an agent needs to call it correctly is missing.

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 baseline is 3, but the description adds real meaning: memory_id and id are aliases for one record (not two), 'subject is not a lookup key here', and concrete view semantics (history = events/resolutions; calibration = posterior/triad/Brier). It goes beyond the schema descriptions.

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 (read/explain) and resource (one memory's stored explanation) with explicit scope qualifier '— not a ranked list.' It names the views it returns (node/history/calibration) and clearly differentiates from memory_recall and memory_observe.

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?

Explicit when-to-use ('when you have a memory_id and need the stored explanation') and when-not ('Do not use it for ranked adaptive recall or appending an observation'), naming the alternative tools. Also notes 'There is no memory_delete' to redirect any deletion intent.

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