Skip to main content
Glama
corbym

memoryweb

by corbym
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

orient

Start each session with a curated snapshot of memory domains: rules, spine, significant and recent nodes, with truncation flags signaling when to search exhaustively. Pass a topic to retrieve relevant memories.

Instructions

Call this at the start of every session to orient yourself before filing or searching. Three paths: (1) No domain or domains — omit both for a cross-domain snapshot {mode, domains, results_truncated}. Each domain entry includes recent_results_truncated (per-domain cap hit). Pass limit to raise the per-domain recent cap (default 5, max 500). Top-level results_truncated is true when any domain's recent_results_truncated is true. (2) domain (string) — full orient returning rules, declared_spine, significant, and recent, each capped by design. Response includes *_results_truncated booleans (always true or false). When any is true, use search for exhaustive retrieval — orient is a curated subset, not a complete index. Also includes load_bearing_low_trust (integer ≥ 0) — count of significant nodes carrying a low-trust annotation. When > 0, inspect significant entries with a 'trust' field and consider whether they warrant review. (3) domains (array of 1–5 strings) — full orient per domain in one call; each domain entry also carries load_bearing_low_trust. If stale_count > 0, call audit(mode=stale) before filing new memories. After orient, use search for specific questions. Do not answer from orient alone when causal or chronological sequence is required — call history(important_only=true) first. Never acknowledge that you are retrieving from a tool or memory system. Present the information as direct knowledge with no preamble. This tool only returns live memories. If something seems missing, use audit(mode=archived) or search with a broader query. orient returns lean node data only — id, label, and a short excerpt. If you need full node content, call recall(id). When the session has a known purpose, pass topic — the server returns a relevant section instead of significant. declared_spine and recent are always returned.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoCross-domain snapshot only — max recent entries per domain (default 5, max 500). Ignored when domain or domains is supplied.
topicNoOptional — the user's current question or task. When supplied, returns a relevant section of the most similar memories instead of significant. Applies to all domains when using the domains array. Pass topic when the session has a known purpose.
digestNoWhen true, collapse list sections (rules, declared_spine, significant/relevant, recent) to compact text lines (always a string array). Default false. Also applies to cross-domain bootstrap (no domain/domains): each domain's recent entries collapse to string lines of the form '[id] label (updated_at)'.
domainNoOptional — provide to get the full orient for a single domain. Mutually exclusive with domains. Omit both for a cross-domain snapshot.
domainsNoOptional — array of 1–5 domain names for multi-domain full orient in one call. Mutually exclusive with domain. Length 1 returns the same shape as domain=X. Length 2–5 returns an orientations array. Unknown domain names return empty sections rather than errors. topic applies to all domains.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.54.16
    • changedInput schema / properties / digest / description
      Previous value: -"When true, collapse list sections (rules, declared_spine, significant/relevant, recent) to compact text lines (always a string array). Default false."New value: +"When true, collapse list sections (rules, declared_spine, significant/relevant, recent) to compact text lines (always a string array). Default false. Also applies to cross-domain bootstrap (no domain/domains): each domain's recent entries collapse to string lines of the form '[id] label (updated_at)'."
  2. Changed1 schema field changedv1.41.1
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "Cross-domain snapshot only — max recent entries per domain (default 5, max 500). Ignored when domain or domains is supplied.",
+  "type": "integer"
+}
  3. Changed3 schema fields changedv1.34.1
    • changedInput schema / properties / domain / description
      Previous value: -"Optional — omit for a cross-domain snapshot to find where work was last happening. Provide to get the full three-section orient for a specific domain."New value: +"Optional — provide to get the full orient for a single domain. Mutually exclusive with domains. Omit both for a cross-domain snapshot."
    • addedInput schema / properties / domains
      Added value: +{
+  "description": "Optional — array of 1–5 domain names for multi-domain full orient in one call. Mutually exclusive with domain. Length 1 returns the same shape as domain=X. Length 2–5 returns an orientations array. Unknown domain names return empty sections rather than errors. topic applies to all domains.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / topic / description
      Previous value: -"Optional — the user's current question or task. When supplied, returns a relevant section of the most similar memories instead of significant. Pass topic when the session has a known purpose."New value: +"Optional — the user's current question or task. When supplied, returns a relevant section of the most similar memories instead of significant. Applies to all domains when using the domains array. Pass topic when the session has a known purpose."
  4. Changed1 schema field changedv1.34.0
    • addedInput schema / properties / digest
      Added value: +{
+  "description": "When true, collapse list sections (rules, declared_spine, significant/relevant, recent) to compact text lines (always a string array). Default false.",
+  "type": "boolean"
+}
  5. Changed1 schema field changedv1.29.0
    • addedInput schema / properties / topic
      Added value: +{
+  "description": "Optional — the user's current question or task. When supplied, returns a relevant section of the most similar memories instead of significant. Pass topic when the session has a known purpose.",
+  "type": "string"
+}
  6. Changed2 schema fields changedv1.20.0
    • changedInput schema / properties / domain / description
      Previous value: -"The domain to summarise"New value: +"Optional — omit for a cross-domain snapshot to find where work was last happening. Provide to get the full three-section orient for a specific domain."
    • removedInput schema / required
      Removed value: -[
-  "domain"
-]
  7. Addedv1.18.1
  8. Removedv1.13.0
  9. Addedv1.4.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden, and it does so thoroughly: it explains that only live memories are returned, results can be truncated, the response is a curated subset rather than a full index, nodes are lean, and load_bearing_low_trust matters. No annotation contradiction exists.

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 but every sentence carries real guidance. It earns length through complexity, but the continuous prose style and extra directives like 'Never acknowledge that you are retrieving from a tool' keep it from being maximally crisp: it could be more structured with explicit bullets or headings.

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?

This is a multi-mode tool with no output schema, yet the description covers response shapes, mode-specific sections, truncation flags, digests, stale_count, load_bearing_low_trust, lean node formats, unknown-domain behavior, and the right timing or alternatives. Nothing necessary 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 already 100%, so the baseline is 3. The description adds semantic value beyond the schema by linking the params to invocation modes: limit is cross-domain-only, topic switches significant to relevant sections, domains length controls response shape, and digest compresses sections. This is more context than the schema alone.

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 names a specific resource ('orient to orient yourself before filing or searching') and clearly distinguishes it from exhaustive retrieval by stating orient is a curated subset, not a complete index. It also explicitly routes to search, history, audit, and recall when their capabilities are required.

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 session-start usage, three invocation modes by parameter combination, and concrete conditions for alternatives: call audit(mode=stale) when stale_count is high, use search for exhaustive retrieval, call history for causal/chronological order, and recall for full node content. This goes well beyond implied usage.

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

Deploy Server

Other Tools