Skip to main content
Glama

webcap

by io.github.shoutsid-lab
OverviewDiscussionsAdmin

webcap_extract

PAID ($0.01, one payment covers a batch of up to 50 URLs): structured content as JSON — title, headings, paragraphs, links, images, document-order markdown. Provide exactly one of "url" (a single page) or "urls" (a batch); "url" is shorthand for a one-item "urls".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoA single page to extract, e.g. https://example.com/. Shorthand for "urls": ["<url>"]. Mutually exclusive with "urls" — sending both is an error.
urlsNoBatch of pages for one payment, at most 50 items; a batch of one is allowed. Mutually exclusive with "url" — sending both is an error.
schemaNoOptional natural-language description of the JSON to extract. Omit it to get the default page structure.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / oneOf
      Added value: +[
+  {
+    "required": [
+      "url"
+    ]
+  },
+  {
+    "required": [
+      "urls"
+    ]
+  }
+]
    • changedInput schema / properties / schema / description
      Previous value: -"Optional natural-language description of the JSON to extract"New value: +"Optional natural-language description of the JSON to extract. Omit it to get the default page structure."
    • changedInput schema / properties / url / description
      Previous value: -"A single page to extract"New value: +"A single page to extract, e.g. https://example.com/. Shorthand for \"urls\": [\"<url>\"]. Mutually exclusive with \"urls\" — sending both is an error."
    • addedInput schema / properties / url / format
      Added value: +"uri"
    • changedInput schema / properties / urls / description
      Previous value: -"Batch (at most 50) for one payment"New value: +"Batch of pages for one payment, at most 50 items; a batch of one is allowed. Mutually exclusive with \"url\" — sending both is an error."
    • addedInput schema / properties / urls / items / format
      Added value: +"uri"
    • addedInput schema / properties / urls / maxItems
      Added value: +50
  2. First observed

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the critical behavioral trait: $0.01, one payment covering a batch of up to 50 URLs. It also scopes the return format. It stops short of payment mechanics (auto-charge timing, failure/refund behavior) and any auth or rate-limit context.

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?

A single dense sentence with the most decision-relevant fact (PAID, price, batch cap) front-loaded, followed by output shape and parameter rules. No filler, though it packs everything into one long clause chain.

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?

No output schema exists, and the description compensates by enumerating the returned structure; the sole optional "schema" parameter is documented in the schema itself. Combined with the disclosed pricing model, this is nearly sufficient for a 3-parameter tool, with the main gap being no routing to the trial 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%, so baseline is 3. The description's statement that "url" is shorthand for a one-item "urls" and that exactly one must be provided merely restates the schema's oneOf and mutual-exclusivity notes rather than adding new meaning.

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?

States a specific verb+resource ("structured content as JSON") and enumerates the returned fields (title, headings, paragraphs, links, images, markdown), so the agent knows exactly what it gets. It implies differentiation from siblings like webcap_capture via the content-oriented output, but never names the near-identical webcap_trial_claim_extract, so sibling routing is left to inference.

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?

The "PAID" prefix hints a fee-based alternative may exist but no when-to-use, when-not-to-use, or alternative tool is named — notably the sibling webcap_trial_claim_extract is never mentioned. The only "provide exactly one of url/urls" line is invocation mechanics, not usage guidance.

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

All webcap toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources