Skip to main content
Glama
piers-fawkes

Fodda Context Layer

by piers-fawkes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

get_evidence

Read-onlyIdempotent

Fetch top evidence, signal scores, and publisher citations for a selected graph node, returning trends with verifiable source URLs.

Instructions

Semantic search across 100+ knowledge graphs returning top trends, signal scores, and hard publisher citations with source URLs.

Input Schema

NameRequiredDescriptionDefault
top_kNoNumber of evidence items to return (default 5)
userIdNoOptional user identifier for trial usage tracking.
graphIdYesThe graph ID. Use list_graphs to see all options. Examples: 'retail', 'tech', 'food', 'travel', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'dentsu-creative-marketing', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'
for_node_idYesThe node_id from a prior search_graph result (e.g. '2507.0'). MUST come from the search result's node_id field. Node IDs are NOT sequential integers — do NOT guess or invent IDs like '1', '2', '3'. Do NOT pass the trend name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.3.3
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / for_node_id / description
      Previous value: -"The ID of the node (Trend or Article)"New value: +"The node_id from a prior search_graph result (e.g. '2507.0'). MUST come from the search result's node_id field. Node IDs are NOT sequential integers — do NOT guess or invent IDs like '1', '2', '3'. Do NOT pass the trend name."
    • changedInput schema / properties / graphId / description
      Previous value: -"The graph ID"New value: +"The graph ID. Use list_graphs to see all options. Examples: 'retail', 'tech', 'food', 'travel', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'dentsu-creative-marketing', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'"
    • changedInput schema / properties / userId / description
      Previous value: -"Unique identifier for the user (Required)"New value: +"Optional user identifier for trial usage tracking."
    • changedInput schema / required
      Previous value: -[
-  "graphId",
-  "for_node_id",
-  "userId"
-]New value: +[
+  "graphId",
+  "for_node_id"
+]
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "evidence": {
-      "description": "Array of evidence items with source URLs, titles, snippets, and relevance scores",
-      "type": "array"
-    },
-    "node_id": {
-      "description": "The node this evidence supports",
-      "type": "string"
-    },
-    "usage": {
-      "properties": {
-        "total_billable_units": {
-          "type": "number"
-        }
-      },
-      "type": "object"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. First observedv1.3.2

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and the closed-world openWorldHint=false, so the safety profile is covered. The description adds useful return-content context (trends, signal scores, cited URLs), but says nothing about auth, rate limits, or that a node lookup is a prerequisite.

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?

A single dense sentence with the retrieval action and its return payload front-loaded. No redundant or filler clauses; every phrase contributes.

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?

There is no output schema, so the description partially compensates by naming the returned fields (trends, signal scores, citations). But it omits the two-step workflow (search_graph → get_evidence) and any pagination/top_k behavior, leaving the agent to infer the calling context.

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%, so all four parameters are already documented in the schema, including the critical warning that for_node_id must come from a prior search result. The description adds no parameter meaning beyond that baseline, which is the expected 3 when the schema does the heavy lifting.

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?

Names a specific verb and resource (semantic search across knowledge graphs) and qualifies the output (top trends, signal scores, publisher citations with source URLs). However, it does not distinguish itself from the sibling search_graph, which the sibling name alone suggests competes for the same 'search' intent.

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?

The description gives no when-to-use or when-not-to-use guidance. It never states that this tool is a follow-up to search_graph or that a prior node result is required — that flow is only discoverable by reading the schema's for_node_id description.

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