Skip to main content
Glama

snapshot

Capture a compact view of the current web page to inspect content, search for elements, and expand specific forms, tables, or sections within a set budget.

Instructions

Current page. expand/more: handles; find: search; within: id's form/table/section.

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
findNo
modeNo
moreNo
budgetNo
expandNo
withinNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

D1.9/5.0
Behavior2/5

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

With no annotations and no output schema, the description carries the full burden and largely drops it: no word on whether snapshots are cached/stale, what refs or handles look like, whether the call consumes a token budget, or what side effects (if any) occur. The only behavioral signal is the scope "current page," and the fragment "expand/more: handles" which vaguely implies handles are returned but never explains them.

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

Conciseness2/5

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

Brevity here is under-specification rather than concision: the note-style fragments are not front-loaded around a clear primary statement of purpose, and the colon-delimited cues read like personal shorthand that an unfamiliar agent cannot reliably parse.

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

Completeness1/5

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

For a six-parameter tool with an enum-driven mode and no annotations or output schema, the description should explain mode semantics, budget behavior, and the shape of the returned snapshot. It provides none of that, leaving the agent unable to reason about cost or correctness before invoking.

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

Parameters2/5

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

Schema description coverage is 0% across six parameters, and the description covers only three of them in telegraphic shorthand (find, within, expand/more), leaving the critical mode enum (minimal/actions/read/full) and budget completely undefined in both places. Even the covered parameters get no format or syntax detail – "within: id's form/table/section" does not say which element the integer refers to.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Current page." only restates the resource implied by the name snapshot and supplies no verb, so the agent must guess whether this captures DOM state, accessibility tree, refs, or text. The parameter fragments hint at capabilities (handle expansion, search, scoping) but never state what the tool actually produces or how it differs from siblings like screenshot or extract.

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

Usage Guidelines2/5

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

There is no when-to-use guidance at all: nothing says whether to call snapshot before act, instead of screenshot, or in place of extract, despite those siblings being the obvious alternatives. The "find: search" fragment weakly implies the tool can be used to locate elements, but that is an in-call hint rather than selection guidance.

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