Skip to main content
Glama

Filters Create

filters_create
Destructive

Creates saved Data Studio filter resources from validated predicate/AND/OR trees, using report fingerprints and dry-run previews to keep writes conflict-checked and reversible.

Instructions

Create saved filter resources from native-validated predicate/and/or trees.

Each item has name, datasource_id and tree (see filter_validate). Requires attached source with matching draft/published; formulas validated by Google. Preserves all existing resources; one journalled report-resource write and read-back. Does not attach new filters to charts/pages/blends or publish drafts. Preview IDs are provisional. Source checks are preflight, not cross-entity CAS. operation_restore removes the created resources if no later consumers/edits conflict.

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": {
      "filters": "<filters>",
      "expected_report_content_fingerprint": "<expected_report_content_fingerprint>"
    },
    "name": "filters_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
filtersYes
report_idNo
expected_report_content_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations it discloses that existing resources are preserved, that the write is a single journalled report-resource write with read-back, that preview IDs are provisional, and that source checks are preflight rather than cross-entity CAS. It also explains that operation_restore can remove created resources when no later consumers conflict, which is exactly the reversibility context an agent needs for a destructive operation.

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?

It is dense and front-loaded, leading with the action and following with constraints, but the later sentences are telegraphic jargon ('preflight, not cross-entity CAS', 'Preview IDs are provisional') that costs the reader more than it saves in length.

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

Completeness5/5

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

For a create tool with an output schema, an annotated destructive flag, and complex nested trees, it covers preconditions, side effects, undo, and partial-failure caveats. Return values need not be described because an output schema exists.

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?

With 0% schema description coverage the description must carry the parameters, and it covers only part of them: name, datasource_id and tree for each filter item, plus a note that formulas are validated by Google. The required expected_report_content_fingerprint and the dry_run flag (which defaults to true) are never explained, leaving the most consequential inputs opaque.

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 opens with a specific verb+resource: 'Create saved filter resources from native-validated predicate/and/or trees.' It points at filter_validate for the tree semantics, implicitly separating construction from validation, but does not directly contrast with the other filter-mutation siblings (filters_update_conditions, page_filters, components_filters).

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?

It states prerequisites ('Requires attached source with matching draft/published'), explicit non-goals ('Does not attach new filters to charts/pages/blends or publish drafts'), and names operation_restore as the undo path. What is missing is a direct statement of when to prefer this over sibling filter tools rather than only what it will not do.

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