santismm-knowledge

Official

by santismm

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Corpus Overview — Start Here

get_overview

Read-onlyIdempotent

Retrieve the complete MCP map to discover core domains, federated surfaces, available tools, identifiers, citation rules, languages, licence terms, bulk-ingest URLs, and reported dataset versions and live counts.

Instructions

Get the complete MCP map — start here. Returns the five-domain core plus the separate Article, Labs, Homeric Atlas, claim-registry, AI-benchmark and Physical AI surfaces, with their tools, identifiers, citation rules, languages, licence and bulk-ingest URLs. Federated surfaces that publish a dataset version report it and their live counts.

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": "get_overview"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`bulk`	Yes
`next`	Yes
`site`	Yes
`total`	Yes
`corpus`	Yes	Whether this copy is current. Compare against the hosted endpoint: a lower total or an older newest_unit means you are holding a snapshot, not that the corpus lacks what you asked for.
`source`	Yes
`domains`	Yes
`license`	Yes
`locales`	Yes
`extensions`	Yes
`license_url`	Yes
`license_spdx`	Yes	SPDX id — check this, not the prose.
`resource_uri`	Yes	Read this same document with resources/read.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.6.0Nov 6, 2026

addedOutput schema / properties / extensions / items / properties / counts

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "number"
+      },
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Live record counts from the federated host's own index."
+}

addedOutput schema / properties / extensions / items / properties / dataset_version

Added value: +{
+  "description": "Version of the federated dataset, read live from its host.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / extensions / items / properties / live

Added value: +{
+  "description": "Whether the live fields could be read on this call.",
+  "enum": [
+    "ok",
+    "unavailable"
+  ],
+  "type": "string"
+}

Changed4 schema fields changedv0.4.1Sep 2, 2026

addedOutput schema / properties / corpus

Added value: +{
+  "additionalProperties": false,
+  "description": "Whether this copy is current. Compare against the hosted endpoint: a lower total or an older newest_unit means you are holding a snapshot, not that the corpus lacks what you asked for.",
+  "properties": {
+    "freshness": {
+      "type": "string"
+    },
+    "newest_unit": {
+      "description": "Newest unit date in THIS copy (YYYY-MM-DD).",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "newest_unit",
+    "freshness"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / extensions

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "citation": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "lookup": {
+        "type": "string"
+      },
+      "source": {
+        "type": "string"
+      },
+      "surface": {
+        "type": "string"
+      },
+      "tools": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "surface",
+      "description",
+      "tools",
+      "source",
+      "lookup",
+      "citation"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / resource_uri

Added value: +{
+  "description": "Read this same document with resources/read.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "source",
-  "site",
-  "locales",
-  "license",
-  "license_spdx",
-  "license_url",
-  "total",
-  "domains",
-  "next",
-  "bulk"
-]New value: +[
+  "resource_uri",
+  "source",
+  "site",
+  "locales",
+  "license",
+  "license_spdx",
+  "license_url",
+  "total",
+  "domains",
+  "extensions",
+  "corpus",
+  "next",
+  "bulk"
+]

First observedv0.2.1Aug 2, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real behaviour beyond that: it discloses the breadth of the payload (federated surfaces with dataset versions and live counts) and that licence and bulk-ingest URLs are included, which an agent could not infer from annotations. It does not say whether 'live counts' means dynamically computed/expensive values, which is a minor gap.

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, front-loaded with the imperative 'start here', and every clause carries content about the return. The middle sentence is a long comma-separated enumeration that is somewhat hard to parse but does not waste words.

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 an output schema present, the description need not spell out the return shape, and it instead conveys scope of coverage — what surfaces and metadata an agent will obtain — which is the right level of detail. Remaining gaps are minor: response size and whether the counts are live/computed are not stated.

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?

The tool takes zero parameters, so there is no parameter semantics to add and the baseline applies. The description correctly implies a parameterless retrieval rather than suggesting configuration options that do not exist.

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 a specific verb and resource ('get the complete MCP map') and enumerates the content: five-domain core, article/labs/Homeric Atlas/claim-registry/AI-benchmark/Physical AI surfaces, tools, identifiers, citation rules, languages, licence and bulk-ingest URLs. That is clearly distinguishable from the list_*, get_* and search_* siblings, which each address one surface. The enumeration is dense and jargon-heavy, but the intent (a catalogue of everything) is unambiguous.

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

Usage Guidelines3/5

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

'Start here' implies it should be the first call before drilling into surface-specific tools, which is useful implied guidance. However, no alternative is named and there is no explicit statement of when-not to use it or whether it needs to be re-called. Guidance is present but inferential rather than stated.

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