Skip to main content
Glama

Reconstruct

by dev.reconstruct
OverviewDiscussionsAdmin

Get component image

get_component_image
Read-onlyIdempotent

Return a WebP cropped to one component candidate's visible rectangle from the saved page screenshot.

Input Schema

NameRequiredDescriptionDefault
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.
elementIdYesZero-based captured element ID from find_elements or get_elements. Must belong to the selected page, view and pinned version.
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
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / elementId / description
      Added value: +"Zero-based captured element ID from find_elements or get_elements. Must belong to the selected page, view and pinned version."
    • addedInput schema / properties / page / description
      Added value: +"Captured page key returned by list_pages or get_application_manifest, not a URL or filesystem path."
    • addedInput schema / properties / product / description
      Added value: +"Product key, for example finance-ozon-ru"
    • addedInput schema / properties / version / description
      Added value: +"Exact capture version returned by list_versions. Pin the same version across related calls; do not use latest as an alias."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$defs": {
+    "image": {
+      "additionalProperties": false,
+      "description": "Metadata for the image in content[contentIndex]; image bytes are not duplicated here",
+      "properties": {
+        "contentIndex": {
+          "const": 0,
+          "description": "Zero-based index of the ImageContentBlock",
+          "type": "integer"
+        },
+        "mimeType": {
+          "description": "MIME type of the returned image",
+          "type": "string"
+        }
+      },
+      "required": [
+        "mimeType",
+        "contentIndex"
+      ],
+      "type": "object"
+    }
+  },
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "description": "Structured result. Existing text or image content remains available in content.",
+  "properties": {
+    "result": {
+      "$ref": "#/$defs/image"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the useful fact that the image is a crop of the visible rectangle from the saved screenshot, but it says nothing about resolution, viewport/DPR handling, or what happens when the element is clipped or off-screen.

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?

One sentence, front-loaded with the output artifact (WebP crop) and then the source (saved page screenshot). No filler, no restatement of the title.

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 an output schema present, the description need not explain the return payload, and the schema fully documents the six inputs. It is complete enough to call confidently, with the only real gap being how the returned crop relates to the requested element's bounds (padding, clipping, scale).

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 all six parameters (including the optional environment with its default) are fully documented in the schema, setting the baseline at 3. The description adds no parameter-level meaning, such as how page/view/version must be pinned together or that elementId is zero-based.

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: returns a WebP cropped to one component candidate's visible rectangle, sourced from the saved page screenshot. That is meaningfully distinct from data-returning siblings like get_component or get_component_styles, though it never explicitly names how it differs from the adjacent image tools (get_page_image, get_element_asset, get_component_assets).

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 explicit when-to-use statement and no named alternative. An agent must infer from the phrase 'component candidate' that this follows list_component_candidates or find_elements and that sibling image tools cover other crops. No prerequisites or exclusions are given.

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

All Reconstruct toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources