Skip to main content
Glama

grab_site

Download a page's assets (images, CSS, fonts, SVG) into a local folder and return a JSON manifest of file paths, palette, and fonts—use when the files themselves are the deliverable.

Instructions

Save the files a read already named. Fetches the page through the same unlock ladder as read_url, downloads its assets (images/icons/css/fonts/svg/inline_svg), and returns a manifest (local paths, plus the palette and fonts those files use) as JSON. Use this when the files are the deliverable. For one URL the read listed, use fetch_asset. Saves into out_dir (a relative folder inside the working directory, or SEARCHTS_MCP_OUT_DIR if the user set it) when given, otherwise a 'searchts-grab-' folder there. A folder that already has files is never written into; the grab goes to '-2', '-3' and so on, and the folder used is returned as out_dir. Set read=true to also save the page text as page.md. max_assets caps how many files are saved (default 120); when it or the byte cap stops early, the manifest's 'omitted' list names every URL left out and why, so never report a grab as complete without reading it. max_tokens is how many radius, shadow, and spacing values to keep (default 24, ceiling 200). When that cap hides real values, tokens_more says how many more and that a higher max_tokens returns them. 'page_rungs' names the fetch tiers tried and what each found. Returns an 'Error: ...' string on failure. Update check: when a newer release exists, a successful result also carries 'update_available' plus, at most once per 24 hours, one line telling the agent. The check is one GET to the GitHub latest release of capad-xyz/searchts, at most once per 24 hours, cached in ~/.searchts/update-check.json, with a searchts User-Agent and nothing about the user. Nothing is installed or changed. SEARCHTS_NO_UPDATE_CHECK=1 turns the check and the note off.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "grab_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
readNo
out_dirNo
max_assetsNo
max_tokensNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.20.0
    • addedInput schema / properties / max_assets
      Added value: +{
      +  "default": 120,
      +  "title": "Max Assets",
      +  "type": "integer"
      +}
    • addedInput schema / properties / max_tokens
      Added value: +{
      +  "default": 24,
      +  "title": "Max Tokens",
      +  "type": "integer"
      +}
  2. Changed10 schema fields changedv0.8.0
    • addedInput schema / properties / out_dir / default
      Added value: +""
    • removedInput schema / properties / out_dir / description
      Removed value: -"Directory to save into (optional; defaults to 'searchts-grab-<host>')."
    • addedInput schema / properties / out_dir / title
      Added value: +"Out Dir"
    • addedInput schema / properties / read / default
      Added value: +false
    • removedInput schema / properties / read / description
      Removed value: -"If true, also save the page text as page.md (default false)."
    • addedInput schema / properties / read / title
      Added value: +"Read"
    • removedInput schema / properties / url / description
      Removed value: -"URL of the page to grab."
    • addedInput schema / properties / url / title
      Added value: +"Url"
    • addedInput schema / title
      Added value: +"grab_site_toolArguments"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "result": {
      +      "title": "Result",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "result"
      +  ],
      +  "title": "grab_site_toolOutput",
      +  "type": "object"
      +}
  3. First observedv0.5.1

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly: it explains folder collision handling, asset caps, omitted-URL reporting, cap-related return fields, error strings, and the update-check side effect. It even warns the agent not to claim completeness without reading the omitted list.

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 front-loaded with the core action and alternative, then packs useful operational details compactly. However, the update-check paragraph is quite long and includes implementation details that could be shortened without losing essential guidance.

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?

Given the tool's complexity, five parameters, no annotations, and an existing output schema, the description is complete. It explains saving behavior, output artifacts, caps, failure mode, and even the side-effectful update check, so an agent has enough context to call it correctly.

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

Parameters5/5

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

Schema description coverage is 0%, but the description compensates for every parameter: url is the page to grab, read optionally saves page.md, out_dir controls the output folder, max_assets caps saved files, and max_tokens caps retained design tokens. It adds defaults and behavioral meaning well beyond the bare schema.

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 description uses a specific verb and resource: it saves files/assets from a page that a read already named, returns a manifest, and explicitly distinguishes the tool from fetch_asset and read_url. An agent can immediately tell this is a multi-asset grab-and-save tool rather than a single-asset fetcher.

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

Usage Guidelines5/5

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

It explicitly says to use this when the files are the deliverable, and directly names fetch_asset as the alternative for a single listed URL. It also clarifies out_dir behavior and the read=true option, leaving little ambiguity about when to choose this tool.

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