Skip to main content
Glama
LiLara-AI

ShadowGraph

Official

shadowgraph_recall

Read-onlyIdempotent

Retrieve scoped memories and records by fusing lexical, vector, graph-distance, and temporal ranks. Returns only matching items with clear signal availability.

Instructions

Recall scoped memory and records by fusing lexical, vector, graph-distance, and temporal ranks. shadowgraph_search is plain content matching, shadowgraph_retrieve adds graph neighbours, shadowgraph_remember writes memory. Reads only. Every response declares which signals were available, so absent ones are never renamed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
asOfNoISO 8601 instant to select by valid time, returning what was true then rather than now. Also enables temporal ranking.
limitNoMaximum items to return, 1-1000; the default is 50 and completeness.limitSource reports which applied. Out of range is rejected, never silently clamped.
queryNoFree text to rank against. An empty query still returns scope-matching records ranked by the remaining signals.
scopeNoScope selector. Omitted or partial fields mean explicit nulls, not "any": identity is the exact (project, userId, agentId, runId, memoryType, key) tuple, so a run-scoped memory never leaks into a user-only read.
offsetNoItems to skip before this window. Ordering is total and deterministic, so paging cannot drop or duplicate an item.
focalIdNoEntity id to measure graph distance from. Without it the graph signal reports available:false.
projectNoProject to recall from. Defaults to "default" for memory records rather than meaning all projects.
memoryTypeNoRestrict memory candidates to this type.
preferRecentNoEnable temporal ranking against now. Ignored when asOf is supplied, which already selects a point in time.
queryEmbeddingNoCaller-supplied query vector. Omit to use the configured provider; with neither, the semantic signal reports available:false and a reason.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageYesThe window actually applied to the matching items.
itemsYesThe items in this window, in deterministic order.
completenessYesDeclares exactly what this response left out, so a truncated result can never look complete.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed14 schema fields changedv0.40.1
    • addedInput schema / properties / asOf / description
      Added value: +"ISO 8601 instant to select by valid time, returning what was true then rather than now. Also enables temporal ranking."
    • addedInput schema / properties / focalId / description
      Added value: +"Entity id to measure graph distance from. Without it the graph signal reports available:false."
    • changedInput schema / properties / limit / description
      Previous value: -"Page size. Omitted means a declared default, never silent truncation."New value: +"Maximum items to return, 1-1000; the default is 50 and completeness.limitSource reports which applied. Out of range is rejected, never silently clamped."
    • addedInput schema / properties / memoryType / description
      Added value: +"Restrict memory candidates to this type."
    • changedInput schema / properties / offset / description
      Previous value: -"Page offset."New value: +"Items to skip before this window. Ordering is total and deterministic, so paging cannot drop or duplicate an item."
    • addedInput schema / properties / preferRecent / description
      Added value: +"Enable temporal ranking against now. Ignored when asOf is supplied, which already selects a point in time."
    • addedInput schema / properties / project / description
      Added value: +"Project to recall from. Defaults to \"default\" for memory records rather than meaning all projects."
    • addedInput schema / properties / query / description
      Added value: +"Free text to rank against. An empty query still returns scope-matching records ranked by the remaining signals."
    • changedInput schema / properties / queryEmbedding / description
      Previous value: -"Optional caller-supplied vector. When omitted, the configured embedding provider is used."New value: +"Caller-supplied query vector. Omit to use the configured provider; with neither, the semantic signal reports available:false and a reason."
    • addedInput schema / properties / scope / description
      Added value: +"Scope selector. Omitted or partial fields mean explicit nulls, not \"any\": identity is the exact (project, userId, agentId, runId, memoryType, key) tuple, so a run-scoped memory never leaks into a user-only read."
    • addedInput schema / properties / scope / properties / agentId / description
      Added value: +"Agent this memory belongs to, or null for none."
    • addedInput schema / properties / scope / properties / runId / description
      Added value: +"Single run or task this memory belongs to, or null for none."
    • addedInput schema / properties / scope / properties / userId / description
      Added value: +"Person this memory belongs to, or null for none."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "description": "Fused results with a per-signal explanation of how they were ranked.",
      +  "properties": {
      +    "completeness": {
      +      "description": "Declares exactly what this response left out, so a truncated result can never look complete.",
      +      "properties": {
      +        "complete": {
      +          "description": "True only when every matching item is present.",
      +          "type": "boolean"
      +        },
      +        "limitSource": {
      +          "description": "Whose choice bounded the result.",
      +          "enum": [
      +            "caller",
      +            "default"
      +          ],
      +          "type": "string"
      +        },
      +        "losslessItems": {
      +          "description": "Always true: each returned item is a full-fidelity record, never a summary or a truncated field.",
      +          "type": "boolean"
      +        },
      +        "omitted": {
      +          "description": "total minus returned.",
      +          "minimum": 0,
      +          "type": "integer"
      +        },
      +        "ranking": {
      +          "description": "How the per-signal lists were fused.",
      +          "properties": {
      +            "k": {
      +              "description": "Reciprocal rank fusion constant.",
      +              "type": "number"
      +            },
      +            "strategy": {
      +              "description": "Fusion strategy identifier, currently weighted_rrf.",
      +              "type": "string"
      +            },
      +            "weights": {
      +              "description": "Per-signal weights applied during fusion.",
      +              "type": "object"
      +            }
      +          },
      +          "required": [
      +            "strategy",
      +            "k",
      +            "weights"
      +          ],
      +          "type": "object"
      +        },
      +        "returned": {
      +          "description": "Items in this response.",
      +          "minimum": 0,
      +          "type": "integer"
      +        },
      +        "scope": {
      +          "description": "The project, query, and structured filters that produced this result, so it explains its own derivation.",
      +          "type": "object"
      +        },
      +        "signals": {
      +          "description": "Authoritative per-signal availability. A signal that could not run says so instead of being silently dropped or renamed.",
      +          "properties": {
      +            "graph": {
      +              "description": "Graph-distance ranking from focalId.",
      +              "properties": {
      +                "available": {
      +                  "description": "Whether this signal could contribute at all.",
      +                  "type": "boolean"
      +                },
      +                "matched": {
      +                  "description": "Candidates this signal contributed.",
      +                  "minimum": 0,
      +                  "type": "integer"
      +                },
      +                "reason": {
      +                  "anyOf": [
      +                    {
      +                      "type": "string"
      +                    },
      +                    {
      +                      "type": "null"
      +                    }
      +                  ],
      +                  "description": "Why the signal was unavailable, when it was."
      +                }
      +              },
      +              "required": [
      +                "available",
      +                "matched",
      +                "reason"
      +              ],
      +              "type": "object"
      +            },
      +            "lexical": {
      +              "description": "BM25-style lexical matching over declared content.",
      +              "properties": {
      +                "available": {
      +                  "description": "True when the query contained terms.",
      +                  "type": "boolean"
      +                },
      +                "matched": {
      +                  "description": "Candidates the lexical list contributed.",
      +                  "minimum": 0,
      +                  "type": "integer"
      +                },
      +                "terms": {
      +                  "description": "The query terms that were used.",
      +                  "items": {
      +                    "type": "string"
      +                  },
      +                  "type": "array"
      +                }
      +              },
      +              "required": [
      +                "available",
      +                "matched",
      +                "terms"
      +              ],
      +              "type": "object"
      +            },
      +            "semantic": {
      +              "description": "Cosine vector matching. available is false when no compatible query vector or provider existed; the result is then lexical, graph, and temporal only.",
      +              "properties": {
      +                "available": {
      +                  "description": "Whether this signal could contribute at all.",
      +                  "type": "boolean"
      +                },
      +                "matched": {
      +                  "description": "Candidates this signal contributed.",
      +                  "minimum": 0,
      +                  "type": "integer"
      +                },
      +                "reason": {
      +                  "anyOf": [
      +                    {
      +                      "type": "string"
      +                    },
      +                    {
      +                      "type": "null"
      +                    }
      +                  ],
      +                  "description": "Why the signal was unavailable, when it was."
      +                }
      +              },
      +              "required": [
      +                "available",
      +                "matched",
      +                "reason"
      +              ],
      +              "type": "object"
      +            },
      +            "temporal": {
      +              "description": "Recency ranking from asOf or preferRecent.",
      +              "properties": {
      +                "asOf": {
      +                  "anyOf": [
      +                    {
      +                      "type": "string"
      +                    },
      +                    {
      +                      "type": "null"
      +                    }
      +                  ],
      +                  "description": "The point in time selection was made against, or null for now."
      +                },
      +                "available": {
      +                  "description": "Whether recency ranking ran.",
      +                  "type": "boolean"
      +                },
      +                "matched": {
      +                  "description": "Candidates the temporal list contributed.",
      +                  "minimum": 0,
      +                  "type": "integer"
      +                },
      +                "reason": {
      +                  "anyOf": [
      +                    {
      +                      "type": "string"
      +                    },
      +                    {
      +                      "type": "null"
      +                    }
      +                  ],
      +                  "description": "Why recency ranking did not run, when it did not."
      +                }
      +              },
      +              "required": [
      +                "available",
      +                "matched",
      +                "reason",
      +                "asOf"
      +              ],
      +              "type": "object"
      +            }
      +          },
      +          "required": [
      +            "lexical",
      +            "semantic",
      +            "graph",
      +            "temporal"
      +          ],
      +          "type": "object"
      +        },
      +        "total": {
      +          "description": "Items that matched in total.",
      +          "minimum": 0,
      +          "type": "integer"
      +        }
      +      },
      +      "required": [
      +        "scope",
      +        "returned",
      +        "total",
      +        "complete",
      +        "omitted",
      +        "losslessItems",
      +        "limitSource",
      +        "signals",
      +        "ranking"
      +      ],
      +      "type": "object"
      +    },
      +    "items": {
      +      "description": "The items in this window, in deterministic order.",
      +      "items": {
      +        "description": "One recalled record with its per-signal explanation.",
      +        "properties": {
      +          "ranks": {
      +            "description": "Position this item held in each signal list, counting from 1, or null where that signal did not rank it.",
      +            "properties": {
      +              "graph": {
      +                "anyOf": [
      +                  {
      +                    "type": "integer"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Position in the graph-distance list; null when no focalId was supplied."
      +              },
      +              "lexical": {
      +                "anyOf": [
      +                  {
      +                    "type": "integer"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Position in the BM25-style lexical list."
      +              },
      +              "semantic": {
      +                "anyOf": [
      +                  {
      +                    "type": "integer"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Position in the vector list; null when no compatible query vector or provider existed."
      +              },
      +              "temporal": {
      +                "anyOf": [
      +                  {
      +                    "type": "integer"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Position in the recency list; null when neither asOf nor preferRecent was supplied."
      +              }
      +            },
      +            "required": [
      +              "lexical",
      +              "semantic",
      +              "graph",
      +              "temporal"
      +            ],
      +            "type": "object"
      +          },
      +          "reasons": {
      +            "description": "One entry per contributing signal, naming the rank it contributed.",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "record": {
      +            "description": "One stored entity: a decision, attempt, memory, fact, or alternative. Fields vary by kind, and an entity imported from an older schema may carry fewer of them.",
      +            "properties": {
      +              "actor": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Who performed the write."
      +              },
      +              "client": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Which client performed the write."
      +              },
      +              "createdAt": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "ISO 8601 creation time."
      +              },
      +              "id": {
      +                "description": "Stable entity identifier.",
      +                "type": "string"
      +              },
      +              "kind": {
      +                "description": "Entity kind: decision, attempt, memory, fact, relation, review, or alternative.",
      +                "type": "string"
      +              },
      +              "project": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Project namespace; records imported from a schema that predates projects may carry null."
      +              },
      +              "schemaVersion": {
      +                "description": "Storage schema version this entity was written under. A value above the build’s own version is preserved rather than downgraded.",
      +                "type": "integer"
      +              },
      +              "sessionId": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Session identifier recorded with the write."
      +              },
      +              "sourceClass": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Claimed origin class recorded with the write. A claim, never proof."
      +              },
      +              "sourceRaw": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "The original origin label when it differed from sourceClass. Audit only; never evidence."
      +              },
      +              "updatedAt": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "ISO 8601 time of the last change."
      +              }
      +            },
      +            "type": "object"
      +          },
      +          "score": {
      +            "description": "Fused score.",
      +            "type": "number"
      +          },
      +          "scores": {
      +            "description": "The raw value behind each rank, or null where that signal did not rank this item.",
      +            "properties": {
      +              "graph": {
      +                "anyOf": [
      +                  {
      +                    "type": "number"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Hop distance from focalId."
      +              },
      +              "lexical": {
      +                "anyOf": [
      +                  {
      +                    "type": "number"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "BM25-style lexical score."
      +              },
      +              "semantic": {
      +                "anyOf": [
      +                  {
      +                    "type": "number"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "Cosine similarity between the query vector and the stored vector."
      +              },
      +              "temporal": {
      +                "anyOf": [
      +                  {
      +                    "type": "string"
      +                  },
      +                  {
      +                    "type": "null"
      +                  }
      +                ],
      +                "description": "The ISO 8601 validFrom or recordedAt instant recency ordering used, not a number."
      +              }
      +            },
      +            "required": [
      +              "lexical",
      +              "semantic",
      +              "graph",
      +              "temporal"
      +            ],
      +            "type": "object"
      +          }
      +        },
      +        "required": [
      +          "record",
      +          "score",
      +          "ranks",
      +          "scores",
      +          "reasons"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "page": {
      +      "description": "The window actually applied to the matching items.",
      +      "properties": {
      +        "hasMore": {
      +          "description": "True when matching items exist beyond this window.",
      +          "type": "boolean"
      +        },
      +        "limit": {
      +          "description": "Window size applied, whether the caller set it or the default did.",
      +          "minimum": 1,
      +          "type": "integer"
      +        },
      +        "offset": {
      +          "description": "Index of the first item returned.",
      +          "minimum": 0,
      +          "type": "integer"
      +        },
      +        "total": {
      +          "description": "Matching items before the window was applied.",
      +          "minimum": 0,
      +          "type": "integer"
      +        }
      +      },
      +      "required": [
      +        "offset",
      +        "limit",
      +        "total",
      +        "hasMore"
      +      ],
      +      "type": "object"
      +    }
      +  },
      +  "required": [
      +    "items",
      +    "page",
      +    "completeness"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.40.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so 'Reads only' is redundant but harmless. The unique addition is 'Every response declares which signals were available, so absent ones are never renamed', a valuable behavioral guarantee about response transparency beyond the annotations. No contradiction with annotations.

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?

Three sentences with no filler; the core function is front-loaded, followed by sibling differentiation and a behavioral guarantee. Every sentence earns its place.

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?

The description covers operation, scope, safety, signal-availability behavior, and sibling routing, which is complete for a read-only tool with a rich input and output schema. The schema handles parameter details and return values, so nothing essential is missing.

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%, with detailed documentation for all 10 parameters, so the baseline is 3. The description adds high-level context about signal fusion but does not detail specific parameters beyond what the schema already provides.

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 leading verb 'Recall' plus the explicit fusion mechanism ('lexical, vector, graph-distance, and temporal ranks') identifies the operation precisely. It then contrasts with shadowgraph_search and shadowgraph_retrieve, making the function unmistakable and differentiating it from siblings.

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 explicitly names sibling tools and their distinguishing behaviors ('shadowgraph_search is plain content matching, shadowgraph_retrieve adds graph neighbours, shadowgraph_remember writes memory'), giving an agent clear routing criteria. The implication that recall is for when fused ranking is needed is sufficient guidance.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LiLara-AI/shadowgraph'

If you have feedback or need assistance with the MCP directory API, please join our Discord server