Edgepedia

Search Edgepedia

search

Read-onlyIdempotent

Search an encyclopedia for facts about a person, place, thing, event, or concept: Edgepedia, over 300k articles with citations. Pass the subject's name ("Mount Fuji", "photosynthesis"), not a question; other names and misspellings match, and when no title matches, articles whose text does follow, marked match: fulltext. Returns results with id, title, url, and preview text, plus a topic: result when the query names a topic ("painters"); pass an id to fetch. limit and page reach further results.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Which page of results, from 1.
`sort`	No	central = the most-linked subjects first.
`first`	No	true = only the best match.
`limit`	No	Results a page, 1 to 30 (default 10).
`query`	Yes	The name of a subject, or words from an article title.
`topic`	No	Only articles under this topic id (as `fetch` topic:… names it, without "topic:").

Output Schema

TableJSON Schema

Name	Required	Description
`page`	No
`pages`	No	Pages of results at this limit; pass `page` for the next.
`results`	Yes
`did_you_mean`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 7, 2026

addedInput schema / properties / first

Added value: +{
+  "description": "true = only the best match.",
+  "type": "boolean"
+}

addedInput schema / properties / limit

Added value: +{
+  "description": "Results a page, 1 to 30 (default 10).",
+  "maximum": 30,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / page

Added value: +{
+  "description": "Which page of results, from 1.",
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / sort

Added value: +{
+  "description": "central = the most-linked subjects first.",
+  "enum": [
+    "relevance",
+    "central"
+  ],
+  "type": "string"
+}

addedInput schema / properties / topic

Added value: +{
+  "description": "Only articles under this topic id (as `fetch` topic:… names it, without \"topic:\").",
+  "type": "string"
+}

addedOutput schema / properties / page
```
Added value: +{
+  "type": "integer"
+}
```

addedOutput schema / properties / pages

Added value: +{
+  "description": "Pages of results at this limit; pass `page` for the next.",
+  "type": "integer"
+}

addedOutput schema / properties / results / items / properties / canonical_id

Added value: +{
+  "description": "The article's permanent id (ep…); `fetch` takes it, and it outlives an address change.",
+  "type": "string"
+}

Changed1 schema field changedOct 4, 2026

changedOutput schema / properties / results / items / properties / text / description

Previous value: -"The article's opening sentences, or for a topic its article count and place in the tree."New value: +"The corpus snippet when available, otherwise the article opening; for a topic its article count and place in the tree."

Changed2 schema fields changedSep 29, 2026

addedOutput schema / properties / results / items / properties / articles

Added value: +{
+  "description": "A topic only: the articles under it.",
+  "type": "integer"
+}

changedOutput schema / properties / results / items / properties / text / description

Previous value: -"The article's opening sentences."New value: +"The article's opening sentences, or for a topic its article count and place in the tree."

First observedSep 20, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's value is in extra behavior: fuzzy/misspelling matching, the fulltext fallback explicitly marked `match: fulltext`, and the special `topic:` result. It adds real operational context beyond the annotations without contradicting them.

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?

Purpose and the critical 'name, not a question' rule are front-loaded, and every clause carries information (matching behavior, result fields, fallback, next step, pagination). The long em-dash-chained sentences are dense but slightly harder to scan than they need to be.

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

Completeness5/5

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

For a 6-param search tool with a full schema, complete annotations, and an existing output schema, the description covers what an agent needs: what to pass, how matching behaves, what comes back, and how to continue. Nothing material is missing.

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 genuinely adds semantics the schema lacks: what `query` should contain (a subject name, not a question), that alternate names and misspellings still match, and that `limit`/`page` reach further results. It does not explain `sort` or `first`, leaving a couple of gaps.

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

Purpose5/5

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

States a specific verb and resource ('Search an encyclopedia for facts about a person, place, thing, event, or concept'), names the corpus (Edgepedia, 300k+ articles with citations), and implicitly separates itself from the sibling `fetch` by saying 'pass an id to `fetch`'. An agent can distinguish it from fetch/related/resolve without opening a schema.

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?

Gives concrete when-to-use guidance: 'Pass the subject's name ("Mount Fuji", "photosynthesis"), not a question', and routes the follow-up step to `fetch` with a returned id. It does not explicitly say when to prefer `resolve`, `related`, or `connect` over search, so it falls short of full when/when-not/alternatives coverage.

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

All Edgepedia tools Inspect

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.