Skip to main content
Glama
jumodada

DrissionPage MCP Server

by jumodada

Save Screenshot

page_screenshot_save
Destructive

Save a page screenshot to an approved local path, with options for full-page capture or a specific browser tab.

Instructions

Save a screenshot to a local path under DP_MCP_SCREENSHOT_ROOT

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesLocal file path under DP_MCP_SCREENSHOT_ROOT to save screenshot
tab_idNoOptional MCP or native DrissionPage tab id. When omitted, the current tab is captured at call start.
full_pageNoTake a full page screenshot

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.8
    • addedInput schema / properties / tab_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 128,
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional MCP or native DrissionPage tab id. When omitted, the current tab is captured at call start.",
      +  "title": "Tab Id"
      +}
    • changedOutput schema / oneOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "data": {
      -        "additionalProperties": false,
      -        "properties": {
      -          "screenshot": {
      -            "additionalProperties": true,
      -            "title": "Screenshot",
      -            "type": "object"
      -          }
      -        },
      -        "required": [
      -          "screenshot"
      -        ],
      -        "title": "PageScreenshotSaveData",
      -        "type": "object"
      -      },
      -      "message": {
      -        "type": "string"
      -      },
      -      "ok": {
      -        "const": true
      -      }
      -    },
      -    "required": [
      -      "ok",
      -      "message",
      -      "data"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "data": {
      -        "additionalProperties": true,
      -        "type": "object"
      -      },
      -      "error": {
      -        "additionalProperties": false,
      -        "properties": {
      -          "code": {
      -            "type": "string"
      -          },
      -          "details": {
      -            "additionalProperties": true,
      -            "type": "object"
      -          },
      -          "message": {
      -            "type": "string"
      -          }
      -        },
      -        "required": [
      -          "code",
      -          "message"
      -        ],
      -        "type": "object"
      -      },
      -      "message": {
      -        "type": "string"
      -      },
      -      "ok": {
      -        "const": false
      -      }
      -    },
      -    "required": [
      -      "ok",
      -      "message",
      -      "error"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "data": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "screenshot": {
      +            "additionalProperties": true,
      +            "title": "Screenshot",
      +            "type": "object"
      +          },
      +          "tab_id": {
      +            "description": "MCP tab id captured for this operation.",
      +            "maxLength": 128,
      +            "minLength": 1,
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "screenshot",
      +          "tab_id"
      +        ],
      +        "title": "PageScreenshotSaveData",
      +        "type": "object"
      +      },
      +      "message": {
      +        "type": "string"
      +      },
      +      "ok": {
      +        "const": true
      +      }
      +    },
      +    "required": [
      +      "ok",
      +      "message",
      +      "data"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "data": {
      +        "additionalProperties": true,
      +        "type": "object"
      +      },
      +      "error": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "code": {
      +            "type": "string"
      +          },
      +          "details": {
      +            "additionalProperties": true,
      +            "type": "object"
      +          },
      +          "message": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "code",
      +          "message"
      +        ],
      +        "type": "object"
      +      },
      +      "message": {
      +        "type": "string"
      +      },
      +      "ok": {
      +        "const": false
      +      }
      +    },
      +    "required": [
      +      "ok",
      +      "message",
      +      "error"
      +    ],
      +    "type": "object"
      +  }
      +]
  2. Addedv0.7.2
  3. Removedv0.7.2
  4. Addedv0.5.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is partly covered. The description does contribute useful context by revealing that writes are sandboxed under DP_MCP_SCREENSHOT_ROOT, but it never explains the destructive semantics — whether an existing file at that path is overwritten, whether directories are created, or what a failure looks like.

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?

A single front-loaded sentence with no filler, and the scoping constraint is stated rather than buried. It is efficient, though its brevity comes at the cost of the missing behavioral and usage detail scored elsewhere.

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

Completeness2/5

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

An output schema exists, so return values need not be explained. But for a destructive, non-idempotent write tool with a near-identical sibling, the description omits overwrite behavior, the relationship to page_screenshot, and any permission or path-edge constraints — leaving the agent under-informed for a state-changing operation.

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 three parameters (path, tab_id, full_page) are already documented in the schema with useful detail. The description only echoes the path root constraint and adds nothing about tab capture timing or full-page behavior, so the baseline 3 applies.

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?

The description states a specific verb+resource ('Save a screenshot') and adds the destination constraint ('to a local path under DP_MCP_SCREENSHOT_ROOT'), so the agent knows this writes a file rather than just capturing. However, it never contrasts itself with the adjacent sibling page_screenshot, which an agent could easily pick instead, so sibling differentiation is left to inference.

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 / when-not-to-use guidance at all. Given that page_screenshot sits directly in the sibling list and presumably captures without persisting, the absence of any routing advice ('use this instead of page_screenshot when you need the image on disk') is a clear gap.

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