Skip to main content
Glama

Recall Memory

recall_memory
Read-onlyIdempotent

Retrieve stored memories by ID, exact tags, or hybrid ranked search to surface project context, past decisions, and similar errors for debugging and decision-making.

Instructions

Recall memories from AutoMem in one of three modes. The mode is selected by which params you pass.

Mode 1 — ID fetch: pass memory_id to retrieve a single memory by ID. All other params are ignored. Routes to GET /memory/{id} and updates last_accessed.

Mode 2 — Tag enumeration: pass tags + exhaustive: true for paginated exact-match listing (NOT ranked retrieval). Use this for cleanup/audit workflows where ranked retrieval silently undercounts large tag sets. Pair with limit (≤200) and offset. Returns has_more/limit/offset page metadata; next page at next_offset. Tag matching is exact, case-insensitive, any-of mode — tag_match: "prefix" and tag_mode: "all" are rejected in this mode.

Mode 3 — Ranked retrieval (default): hybrid search across vector, keyword, tags, recency, and optional graph expansion. The primary tool for finding relevant context. By default, ranked recall requests current active memories only; set current_only: false for audits.

When to use ranked (mode 3):

  • At conversation start: recall context about the current project/topic

  • Before making decisions: check for past decisions on similar topics

  • When debugging: search for similar past errors and their solutions

  • For complex questions: use expand_entities for multi-hop reasoning

When to use enumeration (mode 2): when you need to know how many memories carry a tag, or to walk all of them for cleanup/migration. Ranked recall ignores low-importance hits — enumeration does not.

Examples:

  • recall_memory({ query: "database architecture decisions", tags: ["my-project"], limit: 5 })

  • recall_memory({ memory_id: "8f3a2c1e-5b7d-4e9a-a1c3-2d4f6b8e0a91" }) // Mode 1

  • recall_memory({ tags: ["benchmark-test"], exhaustive: true, limit: 50 }) // Mode 2 (add offset for later pages)

  • recall_memory({ query: "auth", exclude_tags: ["deprecated"] }) // Mode 3 with exclusion

  • recall_memory({ query: "What is Sarah's sister's job?", expand_entities: true }) // Mode 3 multi-hop

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "recall_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoISO upper bound
sortNotime_* for chronological recaps
tagsNoFilter by tags, e.g. the project slug.
limitNoDefaults to 5 in ranked mode and 20 in enumeration mode. Ranked is clamped to ~50 server-side.
queryNoNatural-language search query.
startNoISO lower bound (alternative to time_query)
formatNotext, items (one block per memory) and detailed (adds type, confidence, metadata keys, relation stubs) show a 400-char content preview; fetch the full record by memory_id. json returns full fields. Every format stays within the response token budget.text
offsetNoEnumeration mode only (`exhaustive: true`). Ranked recall rejects it; raise `limit` instead.
contextNoContext label; boosts matching preferences.
queriesNoSeveral queries; results are deduplicated.
languageNoProgramming language; boosts language-specific memories.
tag_modeNoDefault "any".
embeddingNoVector for direct similarity search.
memory_idNoID fetch mode: returns this one memory and ignores every other param.
min_scoreNoRanked-mode only. Minimum final score.
tag_matchNo"prefix" (ranked default) also matches child tags split at ":" or "/" (`auth` matches `auth:login`); it does not match across hyphens. "exact" matches whole tags. Enumeration mode is always exact.
exhaustiveNoTag enumeration mode: requires `tags`; exact any-of match, `limit` ≤200, pages with `offset`. Rejects `tag_match: "prefix"` and `tag_mode: "all"`.
state_modeNoRanked-mode only. "history" includes superseded/invalidated memories. Prefer over current_only.
time_queryNoe.g. "today", "last week", "last 30 days"
active_pathNoCurrent file path, for language detection.
state_debugNoRanked-mode only. Add suppression IDs and reasons to `state_filter`.
context_tagsNoTags to boost.
current_onlyNoRanked-mode only. Hide archived, not-yet-valid, expired, invalidated or superseded memories.
exclude_tagsNoRanked-mode only. Any match excludes.
priority_idsNoMemory IDs to always include.
recency_biasNoRanked-mode only. "auto" lets the service decide.
context_typesNoMemory types to boost.
adaptive_floorNoRanked-mode only. Apply the service's adaptive score floor.
auto_decomposeNoAdd searches for entities and topics extracted from the query.
relation_limitNoMax relations followed per seed.
scope_fallbackNoRanked-mode only. Fill from outside the tag scope when scoped evidence is weak.
expand_entitiesNoMulti-hop: also recall memories about entities in the seed results.
expansion_limitNoMax expanded memories in total.
per_query_limitNoPer-query limit with `queries` (default 5).
expand_relationsNoFollow graph relations from seed results.
expand_min_strengthNoFollow only relations at least this strong. Not used by entity expansion.
expand_respect_tagsNoRanked-mode only. Keep graph/entity expansion inside the tag scope.
expand_min_importanceNoDrop expanded results below this importance; seeds are never filtered.

Output Schema

NameRequiredDescriptionDefault
modeNo
sortNo
countYes
limitNoEnumeration: page size. A budget-trimmed page shrinks `count` and `limit` to what was returned, so `offset + limit` still starts the next page.
queryNo
offsetNoEnumeration.
queriesNo
resultsYes
entitiesNo
has_moreNoEnumeration: more records exist; continue at `next_offset`.
tag_scopeNo
state_modeNo
truncationNoPresent when the response budget cut anything: applied, omitted_results, reason, omitted_fields (diagnostics dropped), compacted_results (json results shown compact).
next_offsetNoEnumeration, while `has_more`: the next page offset.
exclude_tagsNo
recency_biasNo
score_filterNo
state_filterNoCounts; IDs and reasons only with state_debug.
dedup_removedNo
query_time_msNo
vector_searchNo
scope_fallbackNo
jit_enriched_countNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed72 schema fields changedv0.14.4
    • changedInput schema / properties / active_path / description
      Previous value: -"Current file path for language auto-detection (e.g., \"src/auth.ts\")"New value: +"Current file path, for language detection."
    • changedInput schema / properties / adaptive_floor / description
      Previous value: -"Ranked-mode only. Enable the service's adaptive score floor when filtering weak matches."New value: +"Ranked-mode only. Apply the service's adaptive score floor."
    • changedInput schema / properties / auto_decompose / description
      Previous value: -"Auto-extract entities and topics from query to generate supplementary searches."New value: +"Add searches for entities and topics extracted from the query."
    • changedInput schema / properties / context / description
      Previous value: -"Context label (e.g., \"coding-style\", \"architecture\"). Boosts matching preferences."New value: +"Context label; boosts matching preferences."
    • changedInput schema / properties / context_tags / description
      Previous value: -"Priority tags to boost in results (e.g., [\"coding-style\", \"preferences\"])"New value: +"Tags to boost."
    • changedInput schema / properties / context_types / description
      Previous value: -"Priority memory types to boost (e.g., [\"Style\", \"Preference\"])"New value: +"Memory types to boost."
    • changedInput schema / properties / current_only / description
      Previous value: -"Ranked-mode only. When true, server suppresses archived, not-yet-valid, expired, invalidated, or superseded memories from active context."New value: +"Ranked-mode only. Hide archived, not-yet-valid, expired, invalidated or superseded memories."
    • changedInput schema / properties / embedding / description
      Previous value: -"Optional embedding vector for direct similarity search"New value: +"Vector for direct similarity search."
    • changedInput schema / properties / end / description
      Previous value: -"ISO timestamp upper bound"New value: +"ISO upper bound"
    • changedInput schema / properties / exclude_tags / description
      Previous value: -"Ranked-mode only. Tags to exclude from results (any match excludes). Independent of `tag_match` — supports both exact and prefix matching internally on the server."New value: +"Ranked-mode only. Any match excludes."
    • changedInput schema / properties / exhaustive / description
      Previous value: -"MODE: tag enumeration. When true, requires non-empty `tags`. Routes to GET /memory/by-tag for paginated exact-match listing — NOT ranked retrieval. Use for cleanup/audit workflows where ranked recall undercounts. `limit` is clamped to 200. `tag_match: \"prefix\"` and `tag_mode: \"all\"` are rejected in this mode."New value: +"Tag enumeration mode: requires `tags`; exact any-of match, `limit` ≤200, pages with `offset`. Rejects `tag_match: \"prefix\"` and `tag_mode: \"all\"`."
    • changedInput schema / properties / expand_entities / description
      Previous value: -"Enable multi-hop reasoning via entity expansion. Finds memories about people/places mentioned in seed results. Use for \"What is X's sister's job?\" type questions."New value: +"Multi-hop: also recall memories about entities in the seed results."
    • changedInput schema / properties / expand_min_importance / description
      Previous value: -"Minimum importance score for expanded results. Filters out low-relevance memories during graph/entity expansion. Recommended: 0.3-0.5 for broad context, 0.6-0.8 for focused results. Seed results are never filtered, only expanded ones."New value: +"Drop expanded results below this importance; seeds are never filtered."
    • changedInput schema / properties / expand_min_strength / description
      Previous value: -"Minimum relation strength to follow during graph expansion. Only traverses edges above this threshold. Recommended: 0.3 for exploratory, 0.6+ for high-confidence connections only. Does not affect entity expansion."New value: +"Follow only relations at least this strong. Not used by entity expansion."
    • changedInput schema / properties / expand_relations / description
      Previous value: -"Follow graph relationships from seed results to find related memories."New value: +"Follow graph relations from seed results."
    • changedInput schema / properties / expand_respect_tags / description
      Previous value: -"Ranked-mode only. When true, graph/entity expansion stays within the original tag scope; when false, expansion may include related context outside the tags."New value: +"Ranked-mode only. Keep graph/entity expansion inside the tag scope."
    • changedInput schema / properties / expansion_limit / description
      Previous value: -"Max total expanded memories (default: 25)"New value: +"Max expanded memories in total."
    • changedInput schema / properties / format / description
      Previous value: -"Output format: text (default), items (one block per memory, in `results` order, then one bracketed trailing block when there are notes or budget cuts), detailed (adds type/confidence/metadata keys/relation stubs), json (raw per-memory fields incl. full content/metadata/relations; whole-response token budget still applies). text/items/detailed show a content preview (default 400 chars) and keep any stored summary as an additive field — fetch a full record via memory_id."New value: +"text, items (one block per memory) and detailed (adds type, confidence, metadata keys, relation stubs) show a 400-char content preview; fetch the full record by memory_id. json returns full fields. Every format stays within the response token budget."
    • changedInput schema / properties / language / description
      Previous value: -"Programming language hint (e.g., \"python\", \"typescript\"). Prioritizes language-specific memories."New value: +"Programming language; boosts language-specific memories."
    • changedInput schema / properties / limit / description
      Previous value: -"Max memories to return. Schema allows 1–200; in enumeration mode (`exhaustive: true`) the server honors up to 200, while ranked mode is typically clamped server-side to ~50. When omitted, the server defaults to 5 in ranked mode and 20 in enumeration mode."New value: +"Defaults to 5 in ranked mode and 20 in enumeration mode. Ranked is clamped to ~50 server-side."
    • changedInput schema / properties / memory_id / description
      Previous value: -"MODE: ID fetch. When set, fetches the single memory by ID and IGNORES all other params. Routes to GET /memory/{id}; updates last_accessed."New value: +"ID fetch mode: returns this one memory and ignores every other param."
    • changedInput schema / properties / min_score / description
      Previous value: -"Ranked-mode only. Minimum final score threshold before results are returned."New value: +"Ranked-mode only. Minimum final score."
    • changedInput schema / properties / offset / description
      Previous value: -"Enumeration mode only (`exhaustive: true`): records to skip, for paging. Ranked recall has no offset and rejects one; raise `limit` instead."New value: +"Enumeration mode only (`exhaustive: true`). Ranked recall rejects it; raise `limit` instead."
    • changedInput schema / properties / per_query_limit / description
      Previous value: -"Per-query result limit when using queries[] (default: 5)"New value: +"Per-query limit with `queries` (default 5)."
    • changedInput schema / properties / priority_ids / description
      Previous value: -"Specific memory IDs to ensure are included in results"New value: +"Memory IDs to always include."
    • changedInput schema / properties / queries / description
      Previous value: -"Multiple queries for broader recall. Results are deduplicated server-side."New value: +"Several queries; results are deduplicated."
    • changedInput schema / properties / query / description
      Previous value: -"Semantic search query (natural language). Describe what you're looking for."New value: +"Natural-language search query."
    • changedInput schema / properties / recency_bias / description
      Previous value: -"Ranked-mode only. Controls service recency boosting: auto lets the service infer, on forces boosting, off disables it."New value: +"Ranked-mode only. \"auto\" lets the service decide."
    • changedInput schema / properties / relation_limit / description
      Previous value: -"Max relations to follow per seed memory (default: 5)"New value: +"Max relations followed per seed."
    • changedInput schema / properties / scope_fallback / description
      Previous value: -"Ranked-mode only. Allow fallback outside the requested tag scope when scoped recall has weak evidence; diagnostics report tag_scope and outside_tag_scope."New value: +"Ranked-mode only. Fill from outside the tag scope when scoped evidence is weak."
    • changedInput schema / properties / sort / description
      Previous value: -"Result ordering (use time_* for chronological recaps)"New value: +"time_* for chronological recaps"
    • changedInput schema / properties / start / description
      Previous value: -"ISO timestamp lower bound (alternative to time_query)"New value: +"ISO lower bound (alternative to time_query)"
    • changedInput schema / properties / state_debug / description
      Previous value: -"Ranked-mode only. Include state-filter suppression/replacement IDs and reasons when current_only is true."New value: +"Ranked-mode only. Add suppression IDs and reasons to `state_filter`."
    • changedInput schema / properties / state_mode / description
      Previous value: -"Ranked-mode only. `current` returns active memories; `history` allows superseded/invalidated memories for audit timelines. Prefer this over current_only for new clients."New value: +"Ranked-mode only. \"history\" includes superseded/invalidated memories. Prefer over current_only."
    • changedInput schema / properties / tag_match / description
      Previous value: -"\"prefix\" (ranked default) matches tags that start with the value, so `tags: [\"automem\"]` also matches `automem-evals`; \"exact\" matches whole tags only. Enumeration mode is always exact."New value: +"\"prefix\" (ranked default) also matches child tags split at \":\" or \"/\" (`auth` matches `auth:login`); it does not match across hyphens. \"exact\" matches whole tags. Enumeration mode is always exact."
    • changedInput schema / properties / tag_mode / description
      Previous value: -"\"any\" matches memories with any tag (default), \"all\" requires all tags"New value: +"Default \"any\"."
    • changedInput schema / properties / tags / description
      Previous value: -"Filter by tags. Use project name as first tag for scoping."New value: +"Filter by tags, e.g. the project slug."
    • changedInput schema / properties / time_query / description
      Previous value: -"Natural language time filter: \"today\", \"yesterday\", \"last week\", \"last 30 days\""New value: +"e.g. \"today\", \"last week\", \"last 30 days\""
    • removedOutput schema / properties / count / description
      Removed value: -"Number of memories returned"
    • removedOutput schema / properties / dedup_removed / description
      Removed value: -"Number of duplicate results removed (when using multiple queries)"
    • removedOutput schema / properties / entities / description
      Removed value: -"Entity identity diagnostics injected by the service."
    • removedOutput schema / properties / exclude_tags / description
      Removed value: -"Tags excluded from ranked recall."
    • changedOutput schema / properties / has_more / description
      Previous value: -"Enumeration mode only: true if more records exist past this page. Continue at `next_offset`."New value: +"Enumeration: more records exist; continue at `next_offset`."
    • removedOutput schema / properties / jit_enriched_count / description
      Removed value: -"Number of memories enriched inline during recall."
    • changedOutput schema / properties / limit / description
      Previous value: -"Enumeration mode only: page size of this response. When the response budget trims a page, `count` and `limit` shrink to the results returned, so `offset + limit` still starts the next page."New value: +"Enumeration: page size. A budget-trimmed page shrinks `count` and `limit` to what was returned, so `offset + limit` still starts the next page."
    • removedOutput schema / properties / mode / description
      Removed value: -"Mode that produced the result."
    • changedOutput schema / properties / next_offset / description
      Previous value: -"Enumeration mode only, when `has_more` is true: the `offset` for the next page (this offset plus the results returned)."New value: +"Enumeration, while `has_more`: the next page offset."
    • changedOutput schema / properties / offset / description
      Previous value: -"Enumeration mode only: offset used for this response."New value: +"Enumeration."
    • removedOutput schema / properties / queries / description
      Removed value: -"Query variants executed by the service."
    • removedOutput schema / properties / query / description
      Removed value: -"Query text executed by ranked recall."
    • removedOutput schema / properties / query_time_ms / description
      Removed value: -"Service recall latency in milliseconds."
    • removedOutput schema / properties / recency_bias / description
      Removed value: -"Recency bias mode applied by the service."
    • removedOutput schema / properties / results / description
      Removed value: -"Array of matching memories with scores"
    • changedOutput schema / properties / results / items / properties / archived / description
      Previous value: -"json and ID fetch only: true when the memory is archived."New value: +"json and ID fetch only."
    • changedOutput schema / properties / results / items / properties / content / description
      Previous value: -"Memory content (preview-capped in budgeted formats)."New value: +"A preview outside json and ID fetch."
    • changedOutput schema / properties / results / items / properties / content_chars / description
      Previous value: -"Original content length when content was previewed."New value: +"Full length when previewed."
    • changedOutput schema / properties / results / items / properties / content_truncated / description
      Previous value: -"True when content is a preview; fetch the full record via recall_memory({ memory_id })."New value: +"Content is a preview; fetch the full record by memory_id."
    • changedOutput schema / properties / results / items / properties / deduped_from / description
      Previous value: -"Result IDs merged into this result during multi-query deduplication."New value: +"IDs merged into this result by multi-query dedup."
    • removedOutput schema / properties / results / items / properties / jit_enriched / description
      Removed value: -"True when the service enriched the memory during recall."
    • changedOutput schema / properties / results / items / properties / outside_tag_scope / description
      Previous value: -"True when scope_fallback admitted this result outside the requested tag scope."New value: +"Admitted by scope_fallback."
    • changedOutput schema / properties / results / items / properties / state_replaces / description
      Previous value: -"ID of the suppressed memory this result replaced during current-state filtering."New value: +"ID of the suppressed memory this result replaced."
    • changedOutput schema / properties / results / items / properties / summary / description
      Previous value: -"Stored 1-2 sentence summary when the server provides one. Additive in budgeted formats; does not replace content."New value: +"Stored summary; additive to content."
    • changedOutput schema / properties / results / items / properties / t_invalid / description
      Previous value: -"json and ID fetch only: when the memory stopped being valid (set when superseded). Absent while current."New value: +"json and ID fetch only; set when superseded."
    • changedOutput schema / properties / results / items / properties / t_valid / description
      Previous value: -"json and ID fetch only: when the memory became valid."New value: +"json and ID fetch only."
    • removedOutput schema / properties / scope_fallback / description
      Removed value: -"True when recall allowed outside-scope fallback results."
    • removedOutput schema / properties / score_filter / description
      Removed value: -"Score filtering diagnostics such as min_score, adaptive_floor, and filtered_count."
    • removedOutput schema / properties / sort / description
      Removed value: -"Sort mode applied by the service."
    • changedOutput schema / properties / state_filter / description
      Previous value: -"Current-state filtering diagnostics. Includes aggregate counts by default and detailed IDs/reasons only when state_debug=true."New value: +"Counts; IDs and reasons only with state_debug."
    • removedOutput schema / properties / state_mode / description
      Removed value: -"State mode applied by ranked recall."
    • removedOutput schema / properties / tag_scope / description
      Removed value: -"Tag-scope diagnostics including whether scoped evidence was strong enough."
    • changedOutput schema / properties / truncation / description
      Previous value: -"Present when the response budget cut anything: { applied, omitted_results, reason }, plus `omitted_fields` (diagnostics dropped because they did not fit even without results) and `compacted_results` (a json result shown in compact form because it did not fit whole)."New value: +"Present when the response budget cut anything: applied, omitted_results, reason, omitted_fields (diagnostics dropped), compacted_results (json results shown compact)."
    • removedOutput schema / properties / vector_search / description
      Removed value: -"Vector-search diagnostics from the service."
  2. Changed12 schema fields changedv0.14.3
    • changedInput schema / properties / format / description
      Previous value: -"Output format: text (default), items (one block per memory), detailed (adds type/confidence/metadata keys/relation stubs), json (raw per-memory fields incl. full content/metadata/relations; whole-response token budget still applies). text/items/detailed show a content preview (default 400 chars) and keep any stored summary as an additive field — fetch a full record via memory_id."New value: +"Output format: text (default), items (one block per memory, in `results` order, then one bracketed trailing block when there are notes or budget cuts), detailed (adds type/confidence/metadata keys/relation stubs), json (raw per-memory fields incl. full content/metadata/relations; whole-response token budget still applies). text/items/detailed show a content preview (default 400 chars) and keep any stored summary as an additive field — fetch a full record via memory_id."
    • removedInput schema / properties / limit / default
      Removed value: -5
    • changedInput schema / properties / limit / description
      Previous value: -"Max memories to return. Schema allows 1–200; in enumeration mode (`exhaustive: true`) the server honors up to 200, while ranked mode is typically clamped server-side to ~50. Default 5."New value: +"Max memories to return. Schema allows 1–200; in enumeration mode (`exhaustive: true`) the server honors up to 200, while ranked mode is typically clamped server-side to ~50. When omitted, the server defaults to 5 in ranked mode and 20 in enumeration mode."
    • changedInput schema / properties / offset / description
      Previous value: -"Result offset for pagination"New value: +"Enumeration mode only (`exhaustive: true`): records to skip, for paging. Ranked recall has no offset and rejects one; raise `limit` instead."
    • changedInput schema / properties / tag_match / description
      Previous value: -"\"exact\" for exact tag match (default), \"prefix\" for starts-with matching"New value: +"\"prefix\" (ranked default) matches tags that start with the value, so `tags: [\"automem\"]` also matches `automem-evals`; \"exact\" matches whole tags only. Enumeration mode is always exact."
    • changedOutput schema / properties / has_more / description
      Previous value: -"Enumeration mode only: true if more pages exist past `offset + limit`."New value: +"Enumeration mode only: true if more records exist past this page. Continue at `next_offset`."
    • changedOutput schema / properties / limit / description
      Previous value: -"Enumeration mode only: page size used for this response."New value: +"Enumeration mode only: page size of this response. When the response budget trims a page, `count` and `limit` shrink to the results returned, so `offset + limit` still starts the next page."
    • addedOutput schema / properties / next_offset
      Added value: +{
      +  "description": "Enumeration mode only, when `has_more` is true: the `offset` for the next page (this offset plus the results returned).",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / results / items / properties / archived
      Added value: +{
      +  "description": "json and ID fetch only: true when the memory is archived.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / results / items / properties / t_invalid
      Added value: +{
      +  "description": "json and ID fetch only: when the memory stopped being valid (set when superseded). Absent while current.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / t_valid
      Added value: +{
      +  "description": "json and ID fetch only: when the memory became valid.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / truncation / description
      Previous value: -"Present when trailing results were dropped to fit the response budget: { applied, omitted_results, reason }."New value: +"Present when the response budget cut anything: { applied, omitted_results, reason }, plus `omitted_fields` (diagnostics dropped because they did not fit even without results) and `compacted_results` (a json result shown in compact form because it did not fit whole)."
  3. Changed4 schema fields changedv0.14.2
    • changedInput schema / properties / format / description
      Previous value: -"Output format: text (default), items (one block per memory), detailed (adds type/confidence/metadata keys/relation stubs), json (raw per-memory fields incl. full content/metadata/relations; whole-response token budget still applies). text/items/detailed are summary-first: each memory shows its stored 1-2 sentence summary when available, else a content preview — fetch a full record via memory_id."New value: +"Output format: text (default), items (one block per memory), detailed (adds type/confidence/metadata keys/relation stubs), json (raw per-memory fields incl. full content/metadata/relations; whole-response token budget still applies). text/items/detailed show a content preview (default 400 chars) and keep any stored summary as an additive field — fetch a full record via memory_id."
    • changedOutput schema / properties / results / items / properties / content / description
      Previous value: -"Memory content (preview in budgeted formats; omitted when summary is shown)."New value: +"Memory content (preview-capped in budgeted formats)."
    • changedOutput schema / properties / results / items / properties / content_chars / description
      Previous value: -"Original content length when content was previewed or replaced by summary."New value: +"Original content length when content was previewed."
    • changedOutput schema / properties / results / items / properties / summary / description
      Previous value: -"Stored 1-2 sentence summary. In budgeted formats it replaces content when present."New value: +"Stored 1-2 sentence summary when the server provides one. Additive in budgeted formats; does not replace content."
  4. Changed33 schema fields changedv0.14.1
    • addedInput schema / properties / adaptive_floor
      Added value: +{
      +  "description": "Ranked-mode only. Enable the service's adaptive score floor when filtering weak matches.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / current_only
      Added value: +{
      +  "default": true,
      +  "description": "Ranked-mode only. When true, server suppresses archived, not-yet-valid, expired, invalidated, or superseded memories from active context.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / expand_respect_tags
      Added value: +{
      +  "description": "Ranked-mode only. When true, graph/entity expansion stays within the original tag scope; when false, expansion may include related context outside the tags.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / format / description
      Previous value: -"Output format: text (default), items (per-memory), detailed (with metadata), json (raw)"New value: +"Output format: text (default), items (one block per memory), detailed (adds type/confidence/metadata keys/relation stubs), json (raw per-memory fields incl. full content/metadata/relations; whole-response token budget still applies). text/items/detailed are summary-first: each memory shows its stored 1-2 sentence summary when available, else a content preview — fetch a full record via memory_id."
    • addedInput schema / properties / min_score
      Added value: +{
      +  "description": "Ranked-mode only. Minimum final score threshold before results are returned.",
      +  "maximum": 1,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / recency_bias
      Added value: +{
      +  "description": "Ranked-mode only. Controls service recency boosting: auto lets the service infer, on forces boosting, off disables it.",
      +  "enum": [
      +    "auto",
      +    "on",
      +    "off"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / scope_fallback
      Added value: +{
      +  "description": "Ranked-mode only. Allow fallback outside the requested tag scope when scoped recall has weak evidence; diagnostics report tag_scope and outside_tag_scope.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / state_debug
      Added value: +{
      +  "default": false,
      +  "description": "Ranked-mode only. Include state-filter suppression/replacement IDs and reasons when current_only is true.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / state_mode
      Added value: +{
      +  "description": "Ranked-mode only. `current` returns active memories; `history` allows superseded/invalidated memories for audit timelines. Prefer this over current_only for new clients.",
      +  "enum": [
      +    "current",
      +    "history"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / entities
      Added value: +{
      +  "description": "Entity identity diagnostics injected by the service.",
      +  "items": {
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / exclude_tags
      Added value: +{
      +  "description": "Tags excluded from ranked recall.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / jit_enriched_count
      Added value: +{
      +  "description": "Number of memories enriched inline during recall.",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / queries
      Added value: +{
      +  "description": "Query variants executed by the service.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / query
      Added value: +{
      +  "description": "Query text executed by ranked recall.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / query_time_ms
      Added value: +{
      +  "description": "Service recall latency in milliseconds.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / recency_bias
      Added value: +{
      +  "description": "Recency bias mode applied by the service.",
      +  "enum": [
      +    "auto",
      +    "on",
      +    "off"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / content / description
      Added value: +"Memory content (preview in budgeted formats; omitted when summary is shown)."
    • addedOutput schema / properties / results / items / properties / content_chars
      Added value: +{
      +  "description": "Original content length when content was previewed or replaced by summary.",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / results / items / properties / content_truncated
      Added value: +{
      +  "description": "True when content is a preview; fetch the full record via recall_memory({ memory_id }).",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / results / items / properties / deduped_from
      Added value: +{
      +  "description": "Result IDs merged into this result during multi-query deduplication.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / results / items / properties / jit_enriched
      Added value: +{
      +  "description": "True when the service enriched the memory during recall.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / results / items / properties / outside_tag_scope
      Added value: +{
      +  "description": "True when scope_fallback admitted this result outside the requested tag scope.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / results / items / properties / state_replaces
      Added value: +{
      +  "description": "ID of the suppressed memory this result replaced during current-state filtering.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / summary
      Added value: +{
      +  "description": "Stored 1-2 sentence summary. In budgeted formats it replaces content when present.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / updated_at
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / scope_fallback
      Added value: +{
      +  "description": "True when recall allowed outside-scope fallback results.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / score_filter
      Added value: +{
      +  "description": "Score filtering diagnostics such as min_score, adaptive_floor, and filtered_count.",
      +  "type": "object"
      +}
    • addedOutput schema / properties / sort
      Added value: +{
      +  "description": "Sort mode applied by the service.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / state_filter
      Added value: +{
      +  "description": "Current-state filtering diagnostics. Includes aggregate counts by default and detailed IDs/reasons only when state_debug=true.",
      +  "type": "object"
      +}
    • addedOutput schema / properties / state_mode
      Added value: +{
      +  "description": "State mode applied by ranked recall.",
      +  "enum": [
      +    "current",
      +    "history"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / tag_scope
      Added value: +{
      +  "description": "Tag-scope diagnostics including whether scoped evidence was strong enough.",
      +  "type": "object"
      +}
    • addedOutput schema / properties / truncation
      Added value: +{
      +  "description": "Present when trailing results were dropped to fit the response budget: { applied, omitted_results, reason }.",
      +  "type": "object"
      +}
    • addedOutput schema / properties / vector_search
      Added value: +{
      +  "description": "Vector-search diagnostics from the service.",
      +  "type": "object"
      +}
  5. First observedv0.14.0

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered; the description adds real value beyond them by disclosing validation rejections (prefix tag_match and tag_mode 'all' are rejected in enumeration), mode-specific ignored params, page metadata (has_more/limit/offset/next_offset), and the last_accessed side effect of ID fetch. That last_accessed write is a mild tension with readOnlyHint, though it is an incidental access-tracking side effect rather than a resource mutation, so it is not an outright contradiction. It stops short of describing error behavior or what happens when a memory has been superseded.

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 mode routing, then usage guidance, then examples, which is the right order for a 38-parameter tool. It is long but proportionate to the tool's complexity; the main waste is that the Examples block largely restates cases already spelled out in the mode and when-to-use sections.

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 38-parameter, 6-enum, multi-mode tool with an output schema already present, the description covers exactly what structured fields cannot: mode selection, defaults, rejection rules, audit vs. normal use, and worked examples for each path. Return-value details are correctly left to the output schema.

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 per-parameter meaning is already documented and the baseline is 3. The description earns an extra point by explaining cross-parameter semantics the schema cannot express: mode selection derived from which params are passed, which params are ignored or rejected in each mode, and the default-vs-override relationship between current_only and state_mode for audits.

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?

Opens with a specific verb+resource ("Recall memories from AutoMem") and immediately decomposes the tool into three named modes routed by parameters. An agent can distinguish this from store_memory/update_memory/delete_memory or associate_memories purely from the text, without opening the schema.

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?

Gives explicit when-to-use guidance for ranked retrieval (conversation start, before decisions, debugging, multi-hop) and separately for enumeration (counting tag populations, cleanup/migration), plus the key trade-off that ranked recall undercounts because it ignores low-importance hits. It also states the default mode, so an agent knows what happens with no guidance at all.

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