Skip to main content
Glama

Pages Import

pages_import

Copy pages from another report into this one, including their datasources, saved filters, and images. Reuse a redesigned copy in the original report or place imported pages in a new section.

Instructions

Copy pages from another report into this one (copy and paste between reports).

replace={source_page_id: page_id_here} puts a source page's content on an existing page instead of a new one: the page keeps its ID (links, bookmarks), name and navigation place; one journalled page write, undone by operation_restore. Use it to bring a redesign made on a copy back to the original report.

Open both reports with report_open first (the target last, or pass report_id). The source is only read. Brings what the pages need: attaches their reusable datasources, copies the saved filters they reference, creates the pages with conditional formatting (links between imported pages point to the copies), optionally as one navigation section, and re-uploads image files. Each step is journalled and read back; a failure returns status=partial with the steps done. Refuses blends, report variables and datasources embedded in the source. Fingerprint from report_inspect of the target.

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_report_id": "<source_report_id>",
      "page_ids": "<page_ids>",
      "expected_structure_fingerprint": "<expected_structure_fingerprint>"
    },
    "name": "pages_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
replaceNo
page_idsYes
report_idNo
section_nameNo
source_report_idYes
expected_structure_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the substantive behavior: the source is read-only, each step is journalled and read back, failure yields status=partial with the steps done, and the whole write is reversible via operation_restore. It also discloses side effects beyond the page copy itself (datasource attachment, saved-filter copying, image re-upload, link rewriting) and the fingerprint precondition.

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?

The core purpose is front-loaded and the remaining paragraphs are ordered by importance: replace semantics, then prerequisites, then side effects, then refusals. Nearly every clause carries new information, though the fragment 'Fingerprint from report_inspect of the target.' and the dense side-effect sentence make it slightly harder to scan than it needs to be.

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?

For a complex multi-step tool with 7 parameters and 0% schema coverage, it covers the important ground, and the existence of an output schema means return shape needn't be restated. The one omission that matters at call time is dry_run's default-true behavior, which changes what a successful call actually means.

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 description coverage is 0% across 7 parameters, so the description must carry the load, and it explains most of them: replace with its source_page_id-to-page_id shape and its consequence (page keeps ID, name, navigation place), report_id as the alternative to opening the target last, section_name as the optional single navigation section, and expected_structure_fingerprint as coming from report_inspect of the target. The material gap is dry_run, which defaults to true — an agent could believe pages were imported when only a rehearsal ran.

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?

The opening line gives a specific verb and resource plus scope: 'Copy pages from another report into this one (copy and paste between reports).' The parenthetical immediately separates it from pages_create, which makes new pages within a report. An agent can tell which tool performs a cross-report page copy without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states prerequisites ('Open both reports with report_open first (the target last, or pass report_id)') and a concrete scenario for the tricky replace mode: 'Use it to bring a redesign made on a copy back to the original report.' It also names exclusions — blends, report variables, embedded datasources are refused — so the agent knows when this tool will fail rather than attempting it blindly.

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

Deploy Server

Other Tools