Extract up to 200 image URLs, alt text and source attributes; does not fetch images. FREE during validation. No key, credits, wallet or preparation needed. Supply your task in input. Existing source and input limits apply.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| scope | Yes | ||
| total | Yes | ||
| images | Yes | ||
| truncated | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / maxPriceMicroUsdRemoved value: -{
- "description": "Optional legacy field; ignored in free mode.",
- "minimum": 0,
- "type": "integer"
-}Input schema / properties / requestIdRemoved value: -{
- "description": "Optional legacy field; ignored in free mode.",
- "type": "string"
-}Input schema / properties / maxPriceMicroUsd / descriptionPrevious value: -"Explicit maximum new debit; 0 means recovery only."New value: +"Optional legacy field; ignored in free mode."Input schema / properties / maxPriceMicroUsd / maximumRemoved value: -999999999999Input schema / properties / requestId / descriptionPrevious value: -"Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty."New value: +"Optional legacy field; ignored in free mode."Input schema / properties / requestId / patternRemoved value: -"^\\d{13}_[A-Za-z0-9_-]{16,80}$"Input schema / requiredPrevious value: -[
- "input",
- "requestId",
- "maxPriceMicroUsd"
-]New value: +[
+ "input"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description only needs to add behavior beyond that — and it does: a hard 200-result cap, an explicit non-fetch guarantee, and a no-key/no-credits/no-wallet auth posture. 'Existing source and input limits apply' is vague and hints at throttling without quantifying it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The extraction capability is front-loaded and the 'does not fetch images' caveat is well placed. But 'Supply your task in input' is meaningless filler and the 'FREE during validation / No key, credits, wallet...' run reads as marketing padding that dilutes the technical content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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 rightly omitted, and the result cap is disclosed. However, with a nested required input object at 0% schema coverage, the description leaves the agent without any explanation of the html/baseUrl contract or what 'source and input limits' actually constrain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the single parameter is a nested required object with 'html' and 'baseUrl' that carry no documentation anywhere. 'Supply your task in input' adds no meaning about what 'input' must contain or what baseUrl does for relative URL resolution, so the description fails to compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Extract ... image URLs, alt text and source attributes') and pins the scope with 'up to 200' plus the negative 'does not fetch images', which separates it from fetch-oriented siblings like web_readable_fetch. It never names an alternative from the html_* family, so it stops short of full sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Supply your task in input' is the only usage instruction and it says nothing about when this tool is preferable to html_links, html_jsonld, or web_readable_fetch. There are no stated prerequisites, exclusions, or alternative-selection rules.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.