Social Fetch

Generate web page markdown

web_markdown_generate

Read-only

Convert a web page URL into clean markdown.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	No	Alias for `query`. Prefer `query`.
`url`	No	Web page URL to fetch.
`link`	No	Alias for `url`. Prefer `url`.
`path`	No	Alias for `url`. Prefer `url`.
`trim`	No	Ignored if this tool does not support it.
`limit`	No	Ignored if this tool does not support it.
`query`	No	Optional query string used by the bm25 filter to rank relevant content.
`filter`	No	Markdown extraction filter. `fit`: strip boilerplate and extract the main readable content. `raw`: full unfiltered page markdown, no content pruning. `bm25`: rank and return only the content most relevant to `query`, using the BM25 keyword-relevance algorithm — requires `query` to be set.	fit
`offset`	No	Ignored if this tool does not support it.
`context`	Yes	Describe the user's underlying goal in one sentence — not the tool you are calling.
`tweetId`	No	Alias for `url`. Prefer `url`.
`waitFor`	No	Wait for a CSS selector before extraction. Must be prefixed with "css:" (e.g. css:main). JavaScript wait conditions are not supported.
`keywords`	No	Alias for `query`. Prefer `query`.
`pageSize`	No	Ignored if this tool does not support it.
`tweetUrl`	No	Alias for `url`. Prefer `url`.
`tweet_id`	No	Alias for `url`. Prefer `url`.
`cacheMode`	No	Cache behavior. `enabled`: read from cache if present, else fetch and write to cache. `bypass`: always fetch fresh, ignoring and not updating the cache. `write_only`: always fetch fresh, but write the result to cache without reading from it first. Default: `enabled`.	enabled
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`permalink`	No	Alias for `url`. Prefer `url`.
`tweet_url`	No	Alias for `url`. Prefer `url`.
`maxResults`	No	Ignored if this tool does not support it.
`max_results`	No	Ignored if this tool does not support it.
`scanFullPage`	No	When true, scroll the page to load dynamically appended content (infinite scroll). Default false.
`conversation_id`	No	Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed21 schema fields changedSep 21, 2026

addedInput schema / properties / keywords

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `query`. Prefer `query`."
+}

addedInput schema / properties / limit

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / link / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]

removedInput schema / properties / link / type
```
Removed value: -"string"
```

addedInput schema / properties / maxResults

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / max_results

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / offset

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / pageSize

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / path

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `url`. Prefer `url`."
+}

addedInput schema / properties / permalink / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]

removedInput schema / properties / permalink / type
```
Removed value: -"string"
```

addedInput schema / properties / q

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `query`. Prefer `query`."
+}

addedInput schema / properties / trim

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / tweetId / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]

removedInput schema / properties / tweetId / type
```
Removed value: -"string"
```

addedInput schema / properties / tweetUrl / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]

removedInput schema / properties / tweetUrl / type
```
Removed value: -"string"
```

addedInput schema / properties / tweet_id / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]

removedInput schema / properties / tweet_id / type
```
Removed value: -"string"
```

addedInput schema / properties / tweet_url / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]

removedInput schema / properties / tweet_url / type
```
Removed value: -"string"
```

Changed7 schema fields changedSep 12, 2026

addedInput schema / properties / link

Added value: +{
+  "description": "Alias for `url`. Prefer `url`.",
+  "type": "string"
+}

addedInput schema / properties / permalink

Added value: +{
+  "description": "Alias for `url`. Prefer `url`.",
+  "type": "string"
+}

addedInput schema / properties / tweetId

Added value: +{
+  "description": "Alias for `url`. Prefer `url`.",
+  "type": "string"
+}

addedInput schema / properties / tweetUrl

Added value: +{
+  "description": "Alias for `url`. Prefer `url`.",
+  "type": "string"
+}

addedInput schema / properties / tweet_id

Added value: +{
+  "description": "Alias for `url`. Prefer `url`.",
+  "type": "string"
+}

addedInput schema / properties / tweet_url

Added value: +{
+  "description": "Alias for `url`. Prefer `url`.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "url",
-  "context",
-  "llm_model"
-]New value: +[
+  "context",
+  "llm_model"
+]

Changed5 schema fields changedSep 5, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / context

Added value: +{
+  "description": "Describe the user's underlying goal in one sentence — not the tool you are calling.",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "url"
-]New value: +[
+  "url",
+  "context",
+  "llm_model"
+]

Changed1 schema field changedAug 27, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed2 schema fields changedAug 4, 2026

addedInput schema / properties / scanFullPage

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "enum": [
+        "0",
+        "1",
+        "true",
+        "false"
+      ],
+      "type": "string"
+    }
+  ],
+  "description": "When true, scroll the page to load dynamically appended content (infinite scroll). Default false."
+}

addedInput schema / properties / waitFor

Added value: +{
+  "description": "Wait for a CSS selector before extraction. Must be prefixed with \"css:\" (e.g. css:main). JavaScript wait conditions are not supported.",
+  "maxLength": 200,
+  "type": "string"
+}

Changed1 schema field changedJul 31, 2026

changedInput schema / properties / filter / description

Previous value: -"Content filter strategy for markdown extraction. Setting this to `bm25` requires `query` to also be set."New value: +"Markdown extraction filter. `fit`: strip boilerplate and extract the main readable content. `raw`: full unfiltered page markdown, no content pruning. `bm25`: rank and return only the content most relevant to `query`, using the BM25 keyword-relevance algorithm — requires `query` to be set."

Changed3 schema fields changedJul 29, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / cacheMode / description

Previous value: -"Cache behavior. Default: `enabled`."New value: +"Cache behavior. `enabled`: read from cache if present, else fetch and write to cache. `bypass`: always fetch fresh, ignoring and not updating the cache. `write_only`: always fetch fresh, but write the result to cache without reading from it first. Default: `enabled`."

changedInput schema / properties / filter / description

Previous value: -"Content filter strategy for markdown extraction."New value: +"Content filter strategy for markdown extraction. Setting this to `bm25` requires `query` to also be set."

Changed1 schema field changedJul 26, 2026

changedInput schema / properties / cacheMode / description

Previous value: -"Cache behavior. Defaults to enabled."New value: +"Cache behavior. Default: `enabled`."

First observedJul 20, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations (readOnlyHint=true, openWorldHint=true) already declare the safety and dynamism profile, so the description only needs to add context. The word 'clean' hints at boilerplate stripping, which is a behavioral trait. However, it doesn't disclose return format, caching effects, or page-rendering requirements, so the added context is thin but not misleading.

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?

The description is a single tight sentence with no filler, and the core verb+resource is front-loaded. It is concise for the basic operation, though it offers no structural help (e.g., grouping or hints) for the 24-parameter surface.

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

Completeness2/5

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

Given 24 parameters, no output schema, and a large set of overlapping siblings (web_extract_run, web_html_generate, web_crawl_run), a one-sentence description is inadequate. An agent cannot infer what the tool returns (e.g., markdown string vs saved file), how filter modes differ at the tool level, or when to prefer this over a sibling.

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% — every parameter, including aliases, defaults, and enums, has a description. The tool description adds no parameter-level meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

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 uses a specific verb ('Convert') and a clear resource ('a web page URL into clean markdown'), so an agent knows the core operation. It implicitly differentiates from siblings like web_html_generate and web_screenshot_capture, though it doesn't explicitly address the potential overlap with web_extract_run. Clear but not fully distinguishing.

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?

There is no guidance on when to use this tool versus web_extract_run, web_crawl_run, web_html_generate, or web_ask_run. No exclusions or alternatives are named. The intended usage is only implied by the short verb phrase, which leaves an agent to guess among several overlapping web-fetching siblings.

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

All Social Fetch 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.

Generate web page markdown

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources