Skip to main content
Glama
Sign In

Snip

by link.snip
OverviewDiscussionsAdmin

Save and read a web page

save_page

Read a public web page as clean Markdown and save a copy, subject to retention and access settings. Returns the page's text, a short link, QR code and saved-format URLs (.md, .txt, .jpg, .pdf, .mhtml). Successful public copies also return archive_url for the exact version and cite with APA 7, MLA 9, Chicago and BibTeX citations preserving the original source. Those fields are null until a public copy is available. Saving a page does not verify its claims. No account is required. A page saved in the last day may be reused; pass fresh for a new capture.

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": "save_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe http or https page to save.
freshNoLoad the page again even if it was saved in the last day. Default false.
formatsNoOnly these formats (faster for just the text). Default: all of them.
presetsNoOwned Library ids, one per kind. Omit for account defaults; [] skips Library defaults. Explicit link settings win.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / fresh / description
      Previous value: -"Load the page again even if it was saved in the last hour. Default false."New value: +"Load the page again even if it was saved in the last day. Default false."
  2. Changed1 schema field changed
    • addedInput schema / properties / presets
      Added value: +{
+  "description": "Owned Library ids, one per kind. Omit for account defaults; [] skips Library defaults. Explicit link settings win.",
+  "items": {
+    "maxLength": 64,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
  3. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) by disclosing retention/access settings, the one-day reuse cache, that archive_url and citations are null until a public copy exists, that no account is needed, and the explicit scope limit that saving does not verify claims.

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?

Front-loads the core action and each subsequent sentence carries a distinct fact (returns, nullability, no-verification caveat, auth, caching). The middle enumeration of return formats is dense but still earns its place; no filler sentences.

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?

With no output schema, the description carries the return-value burden and does so: text, short link, QR code, format URLs, archive_url, and citation styles. Combined with the caching and auth notes, an agent has everything needed to call it correctly.

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 coverage is 100%, so the baseline is 3. The description reinforces the `fresh` semantics but largely restates what the schema already says ("load again even if saved in the last day"); `formats` and `presets` are not mentioned at all, so it adds little beyond the 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?

States a specific verb + resource ("Read a public web page as clean Markdown and save a copy") and names the artifacts produced. It is clearly distinguishable from siblings like shorten_link or save_collection, which do not fetch page content.

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?

Explains the operating context (public pages only, no account required) and the caching condition with its escape hatch ("a page saved in the last day may be reused; pass fresh for a new capture"). It does not, however, name any alternative tool or state when not to use this one.

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

All Snip toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources