Skip to main content
Glama
Sign In
callimachus

callimachus

by BetaBots-LLC
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

check_decision

Read-only

Check a proposed decision against prior decisions before acting. Returns earlier decisions with dates and status; flags superseded ones and live conflicts so you can ask the user instead of repeating a reverted choice.

Instructions

Contradiction guard: pass a decision you are about to make as proposal. Returns prior decisions with date and status; superseded ones name their replacement. noDecision: not decided yet. Live conflict: ask the user.

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": {
      "proposal": "<proposal>"
    },
    "name": "check_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNoProject path substring. Empty = all projects.
proposalYesThe decision or change you are about to make.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.11.4
    • 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"
+          ]
+        },
+        "noDecision": {
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "facts"
+      ],
+      "type": "object"
+    },
+    {
+      "properties": {
+        "notice": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "notice"
+      ],
+      "type": "object"
+    }
+  ],
+  "type": "object"
+}
  2. Changed4 schema fields changedv0.11.3
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • 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 / proposal / description
      Previous value: -"The change/decision you are about to make. Returns settled decisions on the same topic."New value: +"The decision or change you are about to make."
    • removedInput schema / title
      Removed value: -"CheckDecisionArgs"
  3. Addedv0.6.2

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and does not contradict the guard framing. The description adds real value by disclosing the result vocabulary (date, status, superseded-to-replacement) and the escalation behavior on a live conflict. It does not say whether the check is fuzzy or exact, or how conflicts are detected, which would matter for an agent deciding how much to trust a clean result.

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?

Very short and front-loaded: the guard purpose comes first, then the return contract, then outcome handling. The telegraphic fragments ("noDecision: not decided yet.") are efficient but slightly cryptic and depend on the reader inferring they are result states.

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?

With a read-only annotation set, full schema coverage, and an output schema to carry return values, the description only needs to cover purpose and outcome interpretation, which it does. Remaining gaps are minor: how conflicts are determined and what scope the project filter defaults to are left to the 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 the baseline is 3, but the description adds genuine meaning beyond the schema by framing `proposal` as a hypothetical decision you are about to make rather than a recorded one. That distinction is the crux of using the tool correctly and is not conveyed by the schema text "The decision or change you are about to make" alone in context of the guard semantics.

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

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a concrete verb-plus-resource framing ("Contradiction guard: pass a decision you are about to make as `proposal`") and describes the return shape (prior decisions with date and status, superseded ones naming their replacement). It implicitly separates itself from record_decision and recall_decisions by being a pre-flight check rather than a write or a lookup, though it never names a sibling explicitly.

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?

"pass a decision you are about to make" establishes the trigger point clearly, and the trailing notes give outcome-driven next steps: noDecision means not decided yet, and a live conflict means ask the user. What's missing is any explicit statement of when not to call it (e.g. after the fact, or for already-recorded decisions).

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