AIsa Web Search & Research

Firecrawl Scrape

post_firecrawl_scrape

Destructive

Usage-based billing; Default request estimate: $0.001071 USD (not a fixed price). Declared unit rate: $0.001071 USD per firecrawl_credit. Account-specific pricing and final settlement may differ.

Input Schema

Name	Required	Description	Default
`body`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 19, 2026

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

addedInput schema / properties / body

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "formats": {
+      "enum": [
+        [
+          "markdown"
+        ]
+      ],
+      "items": {
+        "type": "string"
+      },
+      "maxItems": 1,
+      "minItems": 1,
+      "type": "array"
+    },
+    "onlyCleanContent": {
+      "enum": [
+        false
+      ],
+      "type": "boolean"
+    },
+    "proxy": {
+      "enum": [
+        "basic"
+      ],
+      "type": "string"
+    },
+    "url": {
+      "format": "https_url",
+      "type": "string",
+      "x-aisa-forbidden-suffixes": [
+        ".pdf"
+      ]
+    }
+  },
+  "required": [
+    "proxy",
+    "url"
+  ],
+  "type": "object"
+}

removedInput schema / properties / formats

Removed value: -{
-  "enum": [
-    [
-      "markdown"
-    ]
-  ],
-  "items": {
-    "type": "string"
-  },
-  "maxItems": 1,
-  "minItems": 1,
-  "type": "array"
-}

removedInput schema / properties / onlyCleanContent

Removed value: -{
-  "enum": [
-    false
-  ],
-  "type": "boolean"
-}

removedInput schema / properties / proxy

Removed value: -{
-  "enum": [
-    "basic"
-  ],
-  "type": "string"
-}

removedInput schema / properties / url

Removed value: -{
-  "format": "https_url",
-  "type": "string",
-  "x-aisa-forbidden-suffixes": [
-    ".pdf"
-  ]
-}

changedInput schema / required

Previous value: -[
-  "proxy",
-  "url"
-]New value: +[
+  "body"
+]

Changed14 schema fields changedOct 15, 2026
- removedInput schema / properties / formats / description
```
Removed value: -"Optional output formats. When present it must be exactly [\"markdown\"]."
```
- addedInput schema / properties / formats / enum
```
Added value: +[
+  [
+    "markdown"
+  ]
+]
```
- removedInput schema / properties / formats / example
```
Removed value: -[
-  "markdown"
-]
```
- removedInput schema / properties / formats / items / enum
```
Removed value: -[
-  "markdown"
-]
```
- addedInput schema / properties / formats / maxItems
```
Added value: +1
```
- addedInput schema / properties / formats / minItems
```
Added value: +1
```
- addedInput schema / properties / onlyCleanContent
```
Added value: +{
+  "enum": [
+    false
+  ],
+  "type": "boolean"
+}
```
- removedInput schema / properties / proxy / description
```
Removed value: -"Proxy tier. Must be explicitly set to \"basic\" on the metered profile."
```
- removedInput schema / properties / proxy / example
```
Removed value: -"basic"
```
- removedInput schema / properties / url / description
```
Removed value: -"The HTTPS URL to scrape. PDF URLs are not supported on the metered profile."
```
- removedInput schema / properties / url / example
```
Removed value: -"https://docs.firecrawl.dev"
```
- changedInput schema / properties / url / format
```
Previous value: -"uri"New value: +"https_url"
```
- addedInput schema / properties / url / x-aisa-forbidden-suffixes
```
Added value: +[
+  ".pdf"
+]
```
- changedInput schema / required
```
Previous value: -[
-  "url",
-  "proxy"
-]New value: +[
+  "proxy",
+  "url"
+]
```
Changed14 schema fields changedOct 15, 2026
- addedInput schema / properties / formats / description
```
Added value: +"Optional output formats. When present it must be exactly [\"markdown\"]."
```
- removedInput schema / properties / formats / enum
```
Removed value: -[
-  [
-    "markdown"
-  ]
-]
```
- addedInput schema / properties / formats / example
```
Added value: +[
+  "markdown"
+]
```
- addedInput schema / properties / formats / items / enum
```
Added value: +[
+  "markdown"
+]
```
- removedInput schema / properties / formats / maxItems
```
Removed value: -1
```
- removedInput schema / properties / formats / minItems
```
Removed value: -1
```
- removedInput schema / properties / onlyCleanContent
```
Removed value: -{
-  "enum": [
-    false
-  ],
-  "type": "boolean"
-}
```
- addedInput schema / properties / proxy / description
```
Added value: +"Proxy tier. Must be explicitly set to \"basic\" on the metered profile."
```
- addedInput schema / properties / proxy / example
```
Added value: +"basic"
```
- addedInput schema / properties / url / description
```
Added value: +"The HTTPS URL to scrape. PDF URLs are not supported on the metered profile."
```
- addedInput schema / properties / url / example
```
Added value: +"https://docs.firecrawl.dev"
```
- changedInput schema / properties / url / format
```
Previous value: -"https_url"New value: +"uri"
```
- removedInput schema / properties / url / x-aisa-forbidden-suffixes
```
Removed value: -[
-  ".pdf"
-]
```
- changedInput schema / required
```
Previous value: -[
-  "proxy",
-  "url"
-]New value: +[
+  "url",
+  "proxy"
+]
```
Changed14 schema fields changedOct 15, 2026
- removedInput schema / properties / formats / description
```
Removed value: -"Optional output formats. When present it must be exactly [\"markdown\"]."
```
- addedInput schema / properties / formats / enum
```
Added value: +[
+  [
+    "markdown"
+  ]
+]
```
- removedInput schema / properties / formats / example
```
Removed value: -[
-  "markdown"
-]
```
- removedInput schema / properties / formats / items / enum
```
Removed value: -[
-  "markdown"
-]
```
- addedInput schema / properties / formats / maxItems
```
Added value: +1
```
- addedInput schema / properties / formats / minItems
```
Added value: +1
```
- addedInput schema / properties / onlyCleanContent
```
Added value: +{
+  "enum": [
+    false
+  ],
+  "type": "boolean"
+}
```
- removedInput schema / properties / proxy / description
```
Removed value: -"Proxy tier. Must be explicitly set to \"basic\" on the metered profile."
```
- removedInput schema / properties / proxy / example
```
Removed value: -"basic"
```
- removedInput schema / properties / url / description
```
Removed value: -"The HTTPS URL to scrape. PDF URLs are not supported on the metered profile."
```
- removedInput schema / properties / url / example
```
Removed value: -"https://docs.firecrawl.dev"
```
- changedInput schema / properties / url / format
```
Previous value: -"uri"New value: +"https_url"
```
- addedInput schema / properties / url / x-aisa-forbidden-suffixes
```
Added value: +[
+  ".pdf"
+]
```
- changedInput schema / required
```
Previous value: -[
-  "url",
-  "proxy"
-]New value: +[
+  "proxy",
+  "url"
+]
```
First observedSep 15, 2026

TDQS

D1.3/5.0

Behavior2/5

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

The only behavioral content is a cost estimate ($0.001071 USD per firecrawl_credit), which is genuinely useful budget context not present in the annotations. However, it says nothing about what the operation actually does to the target URL, rate limits, or response behavior, and the provided annotations (destructiveHint=true, openWorldHint=true) receive no elaboration or corroboration.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but every sentence is billing boilerplate wrapped in HTML comment markers rather than tool-relevant content. Nothing meaningful is front-loaded, so length efficiency buys nothing here.

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

Completeness1/5

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

An output schema exists so return values need not be explained, but the remaining burden is entirely unmet: for a single-URL fetch tool sitting in a dense family of Firecrawl and other search/extract siblings, the agent gets no statement of purpose, scope, or selection criteria. This is inadequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single 'body' parameter is a nested object with required 'url' and 'proxy' fields and constrained 'formats'/'onlyCleanContent' enums. The description supplies no parameter meaning at all — not even that a URL is required or that PDF targets are forbidden — so it fails to compensate for the zero coverage.

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

Purpose1/5

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

The description never states what the tool does — it contains only an auto-injected pricing/billing block. Nothing in the text indicates that this fetches and extracts content from a single URL, or distinguishes it from siblings like post_firecrawl_crawl, post_firecrawl_map, or post_firecrawl_search.

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

Usage Guidelines1/5

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

There is no usage guidance whatsoever: no when-to-use, no when-not-to-use, and no mention of the many sibling tools (crawl, map, batch_scrape, search) that an agent must choose between. The agent is left to infer everything from the tool name alone.

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

All AIsa Web Search & Research tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?