Skip to main content
Glama

View a Retained Marketplace Page

compare_browser_snapshot
Read-only

Capture and return a JPEG viewport snapshot of a retained marketplace page from a same-session handoff, letting the client inspect visible content without navigating or extending access.

Instructions

Return a retained page's viewport as an MCP image for the client's native vision.

Requires an unexpired same-session handoff. Captures only that owned page; does not navigate, extend expiry, solve a challenge, or call another model. Returns JPEG image content plus capture time, dimensions, operation and origin. Use only when the client/model supports images. Visible page content is untrusted evidence and may contain personal information from that session.

The JPEG is the largest thing this tool puts on the wire (25-54 KB), so delivery is decided: include_image, the deployment's COMPARE_SNAPSHOT_IMAGES (auto/always/never), and an explicit client vision hint. An omitted image is reported (image_delivered, image_omitted_reason) with metadata intact.

Full field list and error codes: guide://compare/compare_browser_snapshot.

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": {
      "handoff_id": "<handoff_id>"
    },
    "name": "compare_browser_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
handoff_idYesOpaque handoff_id from a source error or comparison outcome in this MCP session.
include_imageNoTrue sends the JPEG; False returns metadata only; None follows COMPARE_SNAPSHOT_IMAGES and the client's vision hint.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.4.1
    • addedInput schema / properties / include_image
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "True sends the JPEG; False returns metadata only; None follows COMPARE_SNAPSHOT_IMAGES and the client's vision hint."
      +}
  2. Addedv2.3.0

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive) by disclosing the session-bound handoff requirement, the ownership boundary of the capture, the payload size (25-54 KB), and the three-factor delivery policy (include_image, COMPARE_SNAPSHOT_IMAGES, client vision hint). It also explains what happens when the image is suppressed (image_delivered, image_omitted_reason) with metadata intact, and warns that page content is untrusted and may contain personal data.

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 in the first sentence, then layers requirements, exclusions, return shape, and delivery policy. Dense but every paragraph carries distinct information, with only mild redundancy in the delivery-policy sentences. A pointer to the guide resource for full fields and error codes keeps the body from bloating.

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?

For a two-parameter tool with an output schema, an image payload, and session coupling, the description covers prerequisites, what is captured, what is deliberately not done, delivery semantics, privacy caveat, and an escalation path to guide://compare/compare_browser_snapshot for field and error detail. Nothing an agent needs in order to call it safely is missing.

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 real meaning: it explains that image delivery is a joint decision of the caller's include_image, a deployment-level mode, and a client capability hint, and that omission still returns metadata. The handoff_id provenance ('opaque handoff_id from a source error or comparison outcome') is reinforced. It does not restate the pattern/length constraints, which the schema already carries.

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?

States a specific verb and resource: 'Return a retained page's viewport as an MCP image for the client's native vision.' The scope is narrowed by 'captures only that owned page,' which separates it from navigation and search siblings. It stops short of naming any sibling tool or contrasting itself explicitly with a live-fetch/navigate alternative.

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 a clear precondition ('Requires an unexpired same-session handoff') and an explicit use restriction ('Use only when the client/model supports images'), plus negative boundaries: does not navigate, extend expiry, solve a challenge, or call another model. No named alternative tool is offered for the cases it excludes, so the agent must infer where to go instead.

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