Skip to main content
Glama
Sign In
nokk

nokk

by koloss777
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Remote

snapshot

Converts the current page into a compact numbered outline of headings, text, links, buttons, and form fields, with refs for click or fill; take a new outline after page changes.

Instructions

Show the current page as a compact outline: headings and text in reading order, and every link, button and form field numbered ([e12]) with its name, address or value. Pass a ref to click or fill. Far smaller than read_html; take a new snapshot after the page changes. null when selector matches nothing.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
selectorNoCSS selector of one element; empty for the whole page.
max_charsNoCut the outline after this many characters.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.47-alpha

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations at all, the description carries the behavioral burden and does well: it discloses the output shape (numbered refs like `[e12]`), staleness semantics ('take a new snapshot after the page changes'), the truncation behavior implied by compactness, and the null-on-no-match result. It omits nothing safety-critical for a read operation, though it doesn't state how refs are numbered or that refs may be invalidated between snapshots.

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?

Three dense sentences, front-loaded with what the output looks like, followed by usage and edge-case behavior. No filler; each clause adds either format, usage or fallback information.

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?

An output schema exists, yet the description still explains the ref format agents must act on, plus the null result and re-snapshot cycle — exactly the operational detail an agent needs to chain this with `click`/`fill`.

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 100%, so the baseline is 3, but the description adds meaning beyond it: `selector` returning `null` when nothing matches, and the compact outline being cut rather than erroring. It also explains that the emitted refs (not just parameters) are the payload passed to `click`/`fill`.

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 and resource ('Show the current page as a compact outline') and enumerates exactly what the outline contains: headings, reading-order text, and numbered links/buttons/form fields with names, addresses or values. It also distinguishes itself from the sibling 'read_html' by size and explains the `[e12]` ref format, so an agent can tell what it produces without opening the schema.

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?

Gives explicit usage context: pass refs to `click` or `fill`, and re-snapshot after the page changes, plus the return-null condition when `selector` matches nothing. It names `read_html` as the heavier alternative. It does not differentiate from `read_text`, `links`, or `evaluate`, so the alternative guidance is partial rather than exhaustive.

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