Skip to main content
Glama

View a preserved PDF page

get_source_page_image
Read-only

Returns a stored PDF page as an image so the host can visually inspect scans, diagrams, and tables by specifying the source, version, and page.

Instructions

Return one stored PDF page as an image for the current host's vision capability.

    Page numbers start at 1. Use this for scans, diagrams and tables. The current host
    reads the returned image. Save a reading with record_visual_observation, keeping
    its source_id, version_id and page; visual notes retain their model origin.
    

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": {
      "source_id": "<source_id>"
    },
    "name": "get_source_page_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
source_idYes
version_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real context beyond that: 1-based page numbering, that the image is consumed by the host's vision capability, and that visual notes retain their model origin. It does not disclose failure behavior for missing pages or image format/size, which keeps it below a 5.

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-loaded with the core action, then supporting details. Only mild redundancy between 'for the current host's vision capability' and 'The current host reads the returned image'; everything else earns its place.

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

Completeness3/5

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

A read-only retrieval tool with three parameters and no output schema is reasonably covered, but gaps remain: no note on what happens for out-of-range pages, no indication of image resolution or size limits, and no explanation of the version_id default. Adequate but not 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 0%, so the description must carry the burden. It clarifies 'page' (starts at 1) and ties source_id/version_id to the recording step, but never explains what version_id selects or what happens when it is null, leaving the optional parameter's meaning to guesswork.

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 stored PDF page as an image'. No sibling in the list returns page imagery (get_source, get_claim, get_topic_context return other resources), so an agent can distinguish it on the first sentence alone.

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 positive selection criteria ('Use this for scans, diagrams and tables') and a workflow follow-up (save a reading with record_visual_observation, carrying source_id, version_id and page). It stops short of an explicit exclusion such as 'use get_source for text-only content', but the visual-content framing makes the boundary inferable.

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