Skip to main content
Glama
Sign In
callimachus

callimachus

by BetaBots-LLC
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

recall_decisions

Read-only

Retrieves past decisions with rationale, date, status and thread context via semantic query, helping agents check prior choices before re-deciding and avoid contradictions.

Instructions

Semantic recall of decisions made in past sessions, with rationale, date, status and threadId (replaced ones with include_superseded). Use before re-deciding. Undistilled scopes return the closest sessions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "recall_decisions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax facts (default 10, max 50).
queryYesTopic to recall, e.g. "auth token refresh".
projectNoProject path substring. Empty = all projects.
include_supersededNoAlso return replaced (superseded) facts, each naming what replaced it.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.11.4
    • addedInput schema / properties / include_superseded
      Added value: +{
+  "default": false,
+  "description": "Also return replaced (superseded) facts, each naming what replaced it.",
+  "type": "boolean"
+}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "closestSessions": {
+          "items": {
+            "properties": {
+              "id": {
+                "type": "integer"
+              },
+              "snippet": {
+                "type": "string"
+              },
+              "title": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "required": [
+              "id",
+              "title",
+              "snippet"
+            ],
+            "type": "object"
+          },
+          "type": [
+            "array",
+            "null"
+          ]
+        },
+        "coverage": {
+          "properties": {
+            "distilledThreads": {
+              "type": "integer"
+            },
+            "threads": {
+              "type": "integer"
+            }
+          },
+          "required": [
+            "distilledThreads",
+            "threads"
+          ],
+          "type": [
+            "object",
+            "null"
+          ]
+        },
+        "facts": {
+          "items": {
+            "properties": {
+              "decidedAt": {
+                "type": "integer"
+              },
+              "disputedBy": {
+                "items": {
+                  "properties": {
+                    "decidedAt": {
+                      "type": "integer"
+                    },
+                    "id": {
+                      "type": "integer"
+                    },
+                    "text": {
+                      "type": "string"
+                    },
+                    "threadId": {
+                      "type": [
+                        "integer",
+                        "null"
+                      ]
+                    }
+                  },
+                  "required": [
+                    "id",
+                    "text",
+                    "decidedAt"
+                  ],
+                  "type": "object"
+                },
+                "type": "array"
+              },
+              "extractor": {
+                "type": "string"
+              },
+              "id": {
+                "type": "integer"
+              },
+              "kind": {
+                "type": "string"
+              },
+              "lastConfirmed": {
+                "type": [
+                  "integer",
+                  "null"
+                ]
+              },
+              "match": {
+                "enum": [
+                  "close",
+                  "related",
+                  null
+                ],
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "originRef": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "projectPath": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "rationale": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "replaces": {
+                "items": {
+                  "type": "integer"
+                },
+                "type": "array"
+              },
+              "similarity": {
+                "type": "number"
+              },
+              "source": {
+                "type": "string"
+              },
+              "status": {
+                "enum": [
+                  "current",
+                  "disputed",
+                  "flagged",
+                  "superseded"
+                ],
+                "type": "string"
+              },
+              "supersededBy": {
+                "properties": {
+                  "decidedAt": {
+                    "type": "integer"
+                  },
+                  "id": {
+                    "type": "integer"
+                  },
+                  "text": {
+                    "type": "string"
+                  },
+                  "threadId": {
+                    "type": [
+                      "integer",
+                      "null"
+                    ]
+                  }
+                },
+                "required": [
+                  "id",
+                  "text",
+                  "decidedAt"
+                ],
+                "type": [
+                  "object",
+                  "null"
+                ]
+              },
+              "support": {
+                "type": "integer"
+              },
+              "text": {
+                "type": "string"
+              },
+              "threadId": {
+                "type": "integer"
+              },
+              "title": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "required": [
+              "id",
+              "threadId",
+              "kind",
+              "text",
+              "source",
+              "title",
+              "projectPath",
+              "rationale",
+              "similarity",
+              "extractor",
+              "originRef",
+              "decidedAt",
+              "status",
+              "support"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "hint": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "facts"
+      ],
+      "type": "object"
+    },
+    {
+      "properties": {
+        "notice": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "notice"
+      ],
+      "type": "object"
+    }
+  ],
+  "type": "object"
+}
  2. Changed5 schema fields changedv0.11.3
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • changedInput schema / properties / limit / description
      Previous value: -"Max facts to return (default 20)."New value: +"Max facts (default 10, max 50)."
    • changedInput schema / properties / project / description
      Previous value: -"Substring-match the project path to scope results. Empty = all projects."New value: +"Project path substring. Empty = all projects."
    • changedInput schema / properties / query / description
      Previous value: -"What to recall about (e.g. \"auth token refresh\", \"database migration approach\")."New value: +"Topic to recall, e.g. \"auth token refresh\"."
    • removedInput schema / title
      Removed value: -"RecallArgs"
  3. Addedv0.6.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish a safe read (readOnlyHint=true, openWorldHint=false), so the description is free to add real behavior: semantic (not literal) matching, inclusion of rationale/status metadata, and a degraded path where 'undistilled scopes return the closest sessions'. The phrase 'undistilled scopes' is left undefined, which blunts the value of that disclosure slightly.

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?

Three short sentences with the core capability front-loaded and no filler. The final sentence is telegraphic enough ('Undistilled scopes') that it costs a little clarity while saving space.

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?

An output schema exists, so return values need no prose, and all four params are covered by the schema. Given the read-only nature, the description covers purpose, trigger, and fallback adequately; the undefined 'undistilled' condition is the main remaining gap.

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 coverage is 100% and every parameter is documented, including default and max for limit. The description only restates the superseded behavior already spelled out in the include_superseded schema text, so it adds essentially no meaning beyond the structured fields; baseline 3 applies.

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?

States a specific verb and resource ('Semantic recall of decisions made in past sessions') plus the payload an agent gets back (rationale, date, status, threadId). It is distinguishable from the adjacent record_decision by tense and from recall_gotchas by resource, but it never explicitly contrasts itself with a sibling such as check_decision.

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?

'Use before re-deciding' gives a concrete trigger condition, and the include_superseded note implies when to widen scope. There is no explicit when-not-to-use and no named alternative for single-decision verification, so it stops short of full routing guidance.

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