Skip to main content
Glama

Get page evidence image

get_page_evidence_image
Read-onlyIdempotent

Return one evidence WebP for a page view: a component state (default, hover, focus-visible, disabled, checked…), content revealed by hover or click, the alternate color scheme, an extra viewport width or an embedded frame. Use for visual checks of what the structured evidence describes.

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": {
      "product": "<product>",
      "version": "<version>",
      "page": "<page>",
      "view": "<view>",
      "file": "<file>"
    },
    "name": "get_page_evidence_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesFile name from get_page_summary.evidence or element fields (stateCatalog.screenshots, states[].screenshot, reveals[].file/screenshot, frame.file/screenshot, themeScreenshots, viewportVariants), for example state-12-hover.webp or reveal-12-click.json.
pageYesCaptured page key returned by list_pages or get_application_manifest, not a URL or filesystem path.
viewYesExact stored profile key from list_pages.views (desktop, mobile, numbered profiles or a device label); do not pass the operating system here.
productYesProduct key, for example finance-ozon-ru
versionYesExact capture version returned by list_versions. Pin the same version across related calls; do not use latest as an alias.
environmentNoEnvironment ID from the selected backend platform type in list_platforms.options.platforms[].environments[].id (backend implementation). Omit only when the version has one captured environment. Use captured pairs from list_platforms/list_versions for actual availability.

Output Schema

NameRequiredDescriptionDefault
mimeTypeYesMIME type of the returned image
contentIndexYesZero-based index of the ImageContentBlock

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • removedOutput schema / $defs
      Removed value: -{
      -  "image": {
      -    "additionalProperties": false,
      -    "description": "Metadata for the image in content[contentIndex]; image bytes are not duplicated here",
      -    "properties": {
      -      "contentIndex": {
      -        "const": 0,
      -        "description": "Zero-based index of the ImageContentBlock",
      -        "type": "integer"
      -      },
      -      "mimeType": {
      -        "description": "MIME type of the returned image",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "mimeType",
      -      "contentIndex"
      -    ],
      -    "type": "object"
      -  }
      -}
    • changedOutput schema / description
      Previous value: -"Structured result. Existing text or image content remains available in content."New value: +"Metadata for the image in content[contentIndex]; image bytes are not duplicated here"
    • addedOutput schema / properties / contentIndex
      Added value: +{
      +  "const": 0,
      +  "description": "Zero-based index of the ImageContentBlock",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / mimeType
      Added value: +{
      +  "description": "MIME type of the returned image",
      +  "type": "string"
      +}
    • removedOutput schema / properties / result
      Removed value: -{
      -  "$ref": "#/$defs/image"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "result"
      -]New value: +[
      +  "mimeType",
      +  "contentIndex"
      +]
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive). The description adds meaningful behavior beyond that: exactly one image is returned per call, and the accepted inputs span five distinct evidence categories, which warns the agent it must request images individually rather than expecting a bundle. Return format details are left to the output schema.

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?

Two sentences, front-loaded with the return type, followed by the scope enumeration. The dense parenthetical list of evidence categories is long but each item maps to a real input family, so little is wasted.

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?

With full annotation coverage, 100% schema coverage, and an output schema, the description only needs to convey purpose and evidence scope, which it does. A note on how the single-image-per-call model interacts with large evidence catalogs would make it complete.

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 in detail, including the exact source fields for `file` and the warning not to pass a URL for `page`. The description adds only broad framing of what evidence types exist, not per-parameter meaning, so the baseline 3 applies.

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 ("Return one evidence WebP for a page view") and then enumerates exactly what kinds of evidence it covers: component states, hover/click reveals, alternate color scheme, extra viewport widths, embedded frames. This distinguishes it clearly from data-only siblings like get_page_evidence_data or get_page_image.

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 an explicit use case ("Use for visual checks of what the structured evidence describes"), which frames it as the companion to the structured evidence tool. It lacks explicit when-not guidance or named alternative tools, but the file-parameter text implies the required prerequisite chain via get_page_summary/list_pages/list_versions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources