agent-memory

Overview Schema Source Related Servers Discussions Admin

memory.propose_update

Propose structured updates to project memory files, validated for schema, secrets, and provenance. Changes apply immediately or wait for human review via CLI.

Instructions

Propose one or more structured edits to the project's .agent-memory/ files. Each operation is validated against the schema, scanned for secrets, and checked for required provenance. Depending on the intent and category, the proposal is either applied immediately or staged under .agent-memory/staging// for human review via the apply/reject CLI commands. A rejected proposal is reported in the response body, not as a transport error.

Input Schema

TableJSON Schema

Name	Required	Description
`owner`	No	identifier of the proposing agent; recorded in lock metadata
`intent`	Yes	intent: update_current \| update_shared \| session_log \| add_pitfall \| record_decision \| refresh_module \| update_conventions \| archive_stale
`sources`	No	provenance citations (required for some categories, e.g. decisions)
`grounding`	No	proof-of-grounding receipt from a previous fetch call (SAR-008)
`rationale`	No	short human-readable reason; shown in CLI status and used in the staging-id slug
`confidence`	No	confirmed \| inferred \| user-provided \| stale \| unknown
`operations`	Yes	one or more structured edits to apply

Output Schema

TableJSON Schema

Name	Required	Description
`files`	No	forward-slash relative paths the proposal touched
`reason`	No	on rejection: stable reason code (invalid_intent, secret_detected, ...)
`status`	Yes	applied \| staged \| rejected
`message`	No	human-readable detail to accompany the reason code
`routing`	No	resolved approval routing for traceability
`findings`	No	on secret_detected: per-finding type + line
`warnings`	No	on applied: non-fatal advisories
`applied_at`	No	on applied: RFC3339 UTC write time
`staging_id`	No	on staged: directory name under .agent-memory/staging/
`violations`	No	on validation_failed: per-section schema violations
`index_updated`	No	on applied: whether the FTS index was refreshed
`review_command`	No	on staged: CLI command to inspect the proposal
`affected_sections`	No	on applied: (file, section_id) pairs touched
`staging_ttl_seconds`	No	on staged: seconds until the proposal expires
`provenance_violations`	No	on provenance_violation: list of violation strings
`human_approval_required`	No	on staged: always true — a human must review

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.6.1Sep 26, 2026

addedInput schema / properties / grounding

Added value: +{
+  "additionalProperties": false,
+  "description": "proof-of-grounding receipt from a previous fetch call (SAR-008)",
+  "properties": {
+    "locator": {
+      "type": "string"
+    },
+    "pack_digest": {
+      "type": "string"
+    },
+    "read_nonce": {
+      "type": "string"
+    }
+  },
+  "type": [
+    "null",
+    "object"
+  ]
+}

First observedv0.1.0Jun 3, 2026

TDQS

A4.1/5.0

Behavior5/5

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It reveals several important behaviors: schema validation, secret scanning, provenance checks, immediate vs. staged application, the staging directory path, and that rejections appear in the response body rather than as transport errors. This is unusually transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences long and every sentence earns its place: purpose, process/validation, and edge-case behavior. The most important information is front-loaded, and there is no redundant or vague filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's nested operations schema, seven parameters, and no annotations, the description is fairly complete: it covers validation, security scanning, provenance, staging vs. immediate application, and rejection semantics. The main gap is that it does not specify which intents or categories trigger staging versus immediate application, though the output schema mitigates the need to describe return values.

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%, so the structured schema already documents all seven top-level parameters. The description adds general process context but does not add per-parameter semantic detail beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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: 'Propose one or more structured edits to the project's .agent-memory/ files.' This clearly states the tool's core action. However, it does not explicitly contrast itself with the sibling tools memory.fetch_context and memory.status, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear workflow context: proposals are validated, scanned, checked for provenance, and either applied immediately or staged for human review. This helps an agent understand what will happen when the tool is used, but it does not explicitly state when to choose this tool over the read-oriented siblings or give exclusion criteria.

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

Deploy Server