Skip to main content
Glama

Fetch a URL

fetch
Read-onlyIdempotent

Retrieves a single web page or PDF as Markdown, returning either full text or the top passages that answer a query; optionally renders JavaScript shells when needed.

Instructions

Fetch one URL (page or PDF) as Markdown. query returns only the top_k passages that answer it. content_scope="full" returns the whole page text. render="auto" opens the browser only for a JavaScript shell (up to 3 credits). Returns data.title, content_markdown, content_text, page_text_chars, content_chars, scope_used, language and content_status; fields: https://clawifi.dev/docs/fetch

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": "fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
queryNo
top_kNo
renderNonever
dry_runNoNot supported here: leave it out and use the estimate tool to price a call.
optionsNoOther API fields for this operation, merged into the request body as they are (see the Clawifi API docs).
content_scopeNomain
timeout_secondsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.4.1
    • addedInput schema / properties / content_scope
      Added value: +{
      +  "default": "main",
      +  "title": "Content Scope",
      +  "type": "string"
      +}
    • addedInput schema / properties / dry_run
      Added value: +{
      +  "default": null,
      +  "description": "Not supported here: leave it out and use the estimate tool to price a call.",
      +  "title": "Dry Run"
      +}
    • addedInput schema / properties / options
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Other API fields for this operation, merged into the request body as they are (see the Clawifi API docs).",
      +  "title": "Options"
      +}
    • addedInput schema / properties / query
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Query"
      +}
    • addedInput schema / properties / render
      Added value: +{
      +  "default": "never",
      +  "title": "Render",
      +  "type": "string"
      +}
    • addedInput schema / properties / top_k
      Added value: +{
      +  "default": 5,
      +  "title": "Top K",
      +  "type": "integer"
      +}
  2. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's added value is the cost and side-effect detail: browser rendering only happens for JS shells and can consume up to 3 credits. It also discloses the returned field set, which goes beyond what the annotations say.

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

Conciseness5/5

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

One dense paragraph, front-loaded with the core action, then mode semantics, then return shape. No filler sentences and every clause carries information.

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

Completeness3/5

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

For an 8-parameter tool with 25% schema coverage, three parameters (timeout_seconds, options, content_scope's default) remain undefined anywhere. Listing return fields is somewhat redundant given an output schema exists, so effort is spent where it was least needed.

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

Parameters4/5

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

Schema coverage is only 25%, so the description has to compensate, and it does for the important ones: query semantics (top_k passages that answer it), content_scope="full" vs the "main" default, and render="auto". It leaves timeout_seconds, options, and the default meaning of "main" unexplained.

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?

"Fetch one URL (page or PDF) as Markdown" gives a specific verb, resource, accepted input types, and output format. The emphasis on "one URL" implicitly separates it from crawl/map_site style tools, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

The description explains the mode choices well: query for answer passages, content_scope="full" for the whole page, render="auto" only for JavaScript shells. What it never states is when to prefer this tool over crawl, scrape, search_free, or estimate for pricing a call, so tool-level routing is left to inference.

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