Skip to main content
Glama
Sign In

OneLence

by com.onelence
OverviewDiscussionsAdmin

Evidence gaps

onelence_list_evidence_gaps
Read-onlyIdempotent

Why confidence is limited and what to fix: missing or partial evidence behind sources, campaigns and partners, who must act, and a link to it in OneLence. action is null when OneLence offers no step to take now, for example while evidence is still collecting or a system is unavailable; url is null when the item has no page.

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": "onelence_list_evidence_gaps"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoWindow end, inclusive for a date. Defaults to now.
siteNoSite domain (e.g. example.com) or site id. Defaults to the workspace's newest active site.
limitNoItems to return (default 25).
startNoWindow start: a date (YYYY-MM-DD) or ISO 8601 date-time. Defaults to 30 days before end.
bucketNooperator_action_required = someone must act.
cursorNonext_cursor from the previous call, for more.
source_idNo
entity_typeNo

Output Schema

NameRequiredDescriptionDefault
dataYes
moreNoHow to fetch the next page, when has_more.
noteYes
objectYes
summaryYes
has_moreYes
next_cursorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "data": {
+      "items": {
+        "properties": {
+          "action": {
+            "anyOf": [
+              {
+                "properties": {
+                  "description": {
+                    "anyOf": [
+                      {
+                        "type": "string"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "label": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "label",
+                  "description"
+                ],
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "bucket": {
+            "anyOf": [
+              {
+                "enum": [
+                  "operator_action_required",
+                  "collecting_or_unresolved",
+                  "system_unavailable",
+                  "conflict_requiring_review"
+                ],
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "entity": {
+            "properties": {
+              "id": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "name": {
+                "type": "string"
+              },
+              "source_id": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "type": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "id",
+              "source_id",
+              "name"
+            ],
+            "type": "object"
+          },
+          "needs": {
+            "items": {
+              "properties": {
+                "availability": {
+                  "anyOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "evidence": {
+                  "type": "string"
+                },
+                "owner": {
+                  "anyOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "reason": {
+                  "anyOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                }
+              },
+              "required": [
+                "evidence",
+                "availability",
+                "reason",
+                "owner"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "object": {
+            "const": "evidence_item",
+            "type": "string"
+          },
+          "url": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "entity",
+          "bucket",
+          "needs",
+          "action",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "has_more": {
+      "type": "boolean"
+    },
+    "more": {
+      "description": "How to fetch the next page, when has_more.",
+      "type": "string"
+    },
+    "next_cursor": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "note": {
+      "type": "string"
+    },
+    "object": {
+      "const": "list",
+      "type": "string"
+    },
+    "summary": {
+      "properties": {
+        "blocked": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "missing": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "partial": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "ready": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "total": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "total",
+        "ready",
+        "partial",
+        "missing",
+        "blocked"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "object",
+    "data",
+    "has_more",
+    "next_cursor",
+    "note",
+    "summary"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds genuinely useful interpretation rules — action is null when no step exists, url is null when there is no page — which prevent the agent from misreading empty fields as errors. It stops short of describing pagination behavior or ordering, so it is additive but not rich.

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?

Two sentences, the substance front-loaded, with the null-handling caveat relegated to the second sentence where it belongs. The first sentence is a dense colon-and-comma chain that takes a second pass to parse, but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 optional parameters, an output schema and full annotations, the definition covers purpose and the trickiest output-field semantics, so the core is intact. However, an agent still lacks guidance on bucket selection (three of four enum values are undefined across schema and description), on how site/start/end narrow the gap set, and on how results are ordered — meaningful gaps for a paginated diagnostic list.

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 75%, below the >80% threshold where the schema alone justifies a 3, and the description never discusses start, end, limit, cursor, site or source_id. It does partially compensate on the enums: 'sources, campaigns and partners' maps to entity_type, and 'while evidence is still collecting or a system is unavailable' glosses bucket values the schema leaves undocumented (only operator_action_required is explained there). That partial enum coverage keeps it at a minimum-viable 3 rather than lower.

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 names the resource concretely — 'missing or partial evidence behind sources, campaigns and partners' — and states what the payload answers ('why confidence is limited and what to fix'), which an agent can distinguish from siblings like get_briefing or list_signals. It never uses an explicit list verb ('returns a list of gaps'), so the collection nature is inferred from the tool name rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not guidance, and no sibling is named as an alternative even though get_briefing, get_decision and list_signals sit in the same diagnostic space. The only contextual hint is implicit in the phrase 'why confidence is limited', leaving the agent to guess whether this is a diagnostic tool, an audit tool, or a triage feed.

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

All OneLence toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources