Primary Sources

jina_read

Read-onlyIdempotent

Fetch any URL as clean markdown via Jina Reader (free tier, no key). Use as an extraction fallback when a page is not available as structured data; returns up to 40,000 characters of readable text.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Absolute URL to read, e.g. https://example.com

Output Schema

TableJSON Schema

Name	Required	Description
`data`	Yes	Source payload; fields vary per tool
`source`	Yes	Human-readable upstream source name
`retrievedAt`	Yes	ISO-8601 timestamp of retrieval

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 3, 2026

addedInput schema / properties / url / description

Added value: +"Absolute URL to read, e.g. https://example.com"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "data": {
+      "description": "Source payload; fields vary per tool",
+      "type": "object"
+    },
+    "retrievedAt": {
+      "description": "ISO-8601 timestamp of retrieval",
+      "type": "string"
+    },
+    "source": {
+      "description": "Human-readable upstream source name",
+      "type": "string"
+    }
+  },
+  "required": [
+    "source",
+    "retrievedAt",
+    "data"
+  ],
+  "type": "object"
+}

First observedOct 3, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already carry readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds genuinely new context: free tier with no key, and a concrete output cap of 40,000 characters, which the agent cannot infer from annotations.

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?

Two tightly packed sentences with zero filler. The core action is front-loaded, the fallback guidance follows, and the output-length caveat is appended efficiently.

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?

An output schema exists, so return-value detail is unnecessary, and annotations cover the safety profile. The description complements these with the 40k character limit and no-key access, though it could note any failure modes for unreachable or JS-heavy pages.

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?

Only one parameter with 100% schema description coverage ('Absolute URL to read, e.g. https://example.com'), so the schema carries the semantics. The description adds nothing about the url parameter beyond what the schema already documents; baseline 3 is appropriate.

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 (fetch) plus resource (any URL as clean markdown) and names the mechanism (Jina Reader). The 'free tier, no key' detail lets an agent distinguish it from the many structured-data siblings without opening the 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?

Explicitly frames usage as 'an extraction fallback when a page is not available as structured data,' which routes the agent away from the structured siblings when data is missing. It stops short of naming a specific alternative tool, so it's clear context rather than a full when/when-not/alternative breakdown.

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

All Primary Sources 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.