Skip to main content
Glama
Mingye-Lu

acrawl

by Mingye-Lu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

navigate

Navigate to a URL and return the page content as fit_markdown (default, prunes boilerplate for token efficiency), structured markdown, plain text, or raw HTML.

Instructions

Navigate to a URL and return the page content as fit_markdown (default, prunes boilerplate for token efficiency), structured markdown, plain text, or raw HTML. Automatically escalates from fast HTTP fetch to full headless browser when JavaScript rendering is detected (React, Next.js, Vue, Angular markers, or short bodies). Returns prose content (fit_markdown) plus a YAML accessibility tree structural section for subsequent tool calls. Use this as the primary tool for accessing any web page.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesFully qualified URL to navigate to (must include protocol, e.g. https://example.com). Relative URLs are not supported.
focusNoWhat you are looking for on this page: a short phrase, or a list of them. When semantic pruning is enabled, blocks unrelated to the focus are replaced by '[N blocks pruned]' markers.
formatNoOutput format for page content. 'fit_markdown' (default) prunes boilerplate (navs, footers, ads) before conversion for ~40% token savings; 'markdown' preserves full content with structure; 'text' strips all formatting; 'html' returns raw source. Use 'markdown' if fit_markdown seems to be missing important content.
strip_imagesNoIf true (default), removes image references from output to save context tokens. Set false only when you need image URLs or alt text.
content_depthNoControls how much page content to return. 'main' (default) extracts article/main content only; 'full' returns everything; 'slim' returns first 2000 chars of main content; 'none' skips content entirely (returns page_map only).main
page_map_depthNoControls page_map verbosity. 'slim' (default) omits CSS selectors from elements (use @eN refs instead); 'full' includes raw CSS selectors for all elements; 'none' omits the page_map entirely.slim

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.16.0
    • addedInput schema / properties / focus
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  ],
+  "description": "What you are looking for on this page: a short phrase, or a list of them. When semantic pruning is enabled, blocks unrelated to the focus are replaced by '[N blocks pruned]' markers."
+}
  2. Changed5 schema fields changedv0.10.0
    • addedInput schema / properties / content_depth / description
      Added value: +"Controls how much page content to return. 'main' (default) extracts article/main content only; 'full' returns everything; 'slim' returns first 2000 chars of main content; 'none' skips content entirely (returns page_map only)."
    • addedInput schema / properties / format / description
      Added value: +"Output format for page content. 'fit_markdown' (default) prunes boilerplate (navs, footers, ads) before conversion for ~40% token savings; 'markdown' preserves full content with structure; 'text' strips all formatting; 'html' returns raw source. Use 'markdown' if fit_markdown seems to be missing important content."
    • addedInput schema / properties / page_map_depth / description
      Added value: +"Controls page_map verbosity. 'slim' (default) omits CSS selectors from elements (use @eN refs instead); 'full' includes raw CSS selectors for all elements; 'none' omits the page_map entirely."
    • addedInput schema / properties / strip_images / description
      Added value: +"If true (default), removes image references from output to save context tokens. Set false only when you need image URLs or alt text."
    • addedInput schema / properties / url / description
      Added value: +"Fully qualified URL to navigate to (must include protocol, e.g. https://example.com). Relative URLs are not supported."
  3. First observedv0.1.0

TDQS

A4.1/5.0
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 well: it discloses the automatic HTTP-to-headless escalation with the JS-detection heuristics (React, Next.js, Vue, Angular, short noscript bodies), the composite return of prose plus a YAML accessibility tree, and the token-saving pruning behavior. It omits any mention of auth requirements, rate limits, or page-size caps, so it stops short of a 5.

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?

Four sentences, front-loaded with the purpose and format options, then escalation behavior and return shape. It is dense and earns its space, though the escalation-heuristics sentence is packed tightly and could be slightly leaner.

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?

For a 6-parameter tool with no output schema, the description covers the return structure (fit_markdown prose plus a YAML accessibility tree for follow-up calls) and the fetch-escalation model. It is nearly complete, missing only edge-case behavior for failures or blocked pages.

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 the schema already documents all six parameters well, including enums and defaults. The description largely restates what the schema provides (format options, boilerplate pruning), adding only the ~40% token-savings figure that is itself also in the schema, so the baseline 3 is appropriate.

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?

States a specific verb+resource (navigate to a URL and return page content) and enumerates the four output formats. It explicitly positions itself as the primary web-access tool, which distinguishes it from siblings like read_content, page_map, and refresh.

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

Usage Guidelines4/5

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

'Use this as the primary tool for accessing any web page' gives clear default guidance, and it names a fallback condition ('Use markdown if fit_markdown seems to be missing important content'). However, it never names alternative tools (read_content, page_map) or states when NOT to navigate, so routing among siblings is left partly implicit.

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

Deploy Server

Other Tools