search-boost-mcp

Overview Schema Source Related Servers Discussions Admin

Fetch Page

fetch_page

Read-only

Read a known HTTP(S) URL without searching again, returning readable HTML or extracted PDF text; use bounded windows and nextOffset to continue long pages from cache.

Instructions

Read a known HTTP(S) URL without searching again. Returns readable HTML or locally extracted PDF text, with retrieval route and any extraction limitations. Long bodies use bounded windows; continue from nextOffset using the cached read, not a new request. A focus miss is not evidence of absence: retry without focus. Binary bodies and PDFs with no extractable text return errors, not page text. Network safety, proxy policy, cancellation and size limits remain enforced through all supported fallbacks. This is not an authenticated browser.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	http(s) URL to fetch
`focus`	No	Keep matching paragraphs; omit for the readable body. Output may still be windowed; inspect nextOffset and limitations
`offset`	No	Character offset into the page body (default 0); pass nextOffset from a previous call to continue a long page from cache

Output Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes
`via`	Yes
`offset`	No
`tookMs`	Yes
`content`	Yes
`focusMiss`	No
`truncated`	No
`limitation`	No
`nextOffset`	No
`totalChars`	No
`windowNote`	No
`word_count`	Yes
`requestedUrl`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.2.4Oct 3, 2026

changedInput schema / properties / focus / description

Previous value: -"Keep paragraphs matching these terms (optional; full page is returned when omitted)"New value: +"Keep matching paragraphs; omit for the readable body. Output may still be windowed; inspect nextOffset and limitations"

addedInput schema / properties / offset

Added value: +{
+  "description": "Character offset into the page body (default 0); pass nextOffset from a previous call to continue a long page from cache",
+  "minimum": 0,
+  "type": "integer"
+}

addedOutput schema / properties / nextOffset
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / offset
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / requestedUrl
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / totalChars
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / windowNote
```
Added value: +{
+  "type": "string"
+}
```

Changed3 schema fields changedv0.2.2Sep 22, 2026

changedInput schema / properties / focus / description

Previous value: -"Keep paragraphs matching these terms (~90% token savings)"New value: +"Keep paragraphs matching these terms (optional; full page is returned when omitted)"

addedOutput schema / properties / focusMiss
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / limitation

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "kind": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind",
+    "message"
+  ],
+  "type": "object"
+}

First observedv0.1.2Aug 17, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only cover the safety profile (readOnly, openWorld, non-destructive); the description adds substantial behavior beyond them: binary bodies and text-less PDFs return errors, long bodies are windowed and continued from cache, network safety/proxy/cancellation/size limits persist through fallbacks, and it is explicitly not an authenticated browser. These are exactly the operational caveats an agent needs.

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?

Front-loaded with the core action, then dense but purposeful sentences covering return format, pagination, focus retry, error cases, and the auth boundary. No filler and no repetition of the schema or annotations.

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?

An output schema exists, so return-value documentation is not required, and the description still covers error outcomes, extraction limitations, pagination continuation, and the unauthenticated boundary. Nothing needed to invoke it correctly 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 description coverage is 100%, so the baseline is 3, but the description adds real semantics: offset continuation should use the cached read rather than a new request, and focus should be dropped on a miss because a miss is not evidence of absence. That goes beyond the schema's parameter descriptions without restating them.

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?

The first sentence gives a specific verb (read/fetch) and resource (a known HTTP(S) URL) plus a distinguishing constraint ('without searching again') that separates it from the search siblings. It also states the return shape (readable HTML or locally extracted PDF text with retrieval route). An agent can select this over fused_search or x_search without opening either 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?

It clearly sets the context of use (a URL you already know, avoiding a re-search) and gives concrete recovery guidance: 'A focus miss is not evidence of absence: retry without focus.' It stops short of explicitly naming the search siblings as the alternative when the URL is unknown, so routing is implied rather than spelled out.

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

Deploy Server