Skip to main content
Glama

Groups Filters

groups_filters
Destructive

Set filter IDs and inheritance for multiple report groups in one atomic page update, preserving members and child settings while validating sources and fingerprints.

Instructions

Set group filter IDs and/or inheritance in one page-atomic batch.

Each change: group_id, optional filter_ids (complete list, [] clears), optional inherit_filters. Omitted/null properties stay unchanged. Preserves members, child-group links, controlStatePassThrough, geometry and child settings. Native source validation and advisory direct-member compatibility; no claim of full nested-group/blend traversal or effective runtime inheritance. Refresh viewer first; fingerprints from page_get and filters_list. Attached filter sources with matching draft/published required. Guarded journalled page write/read-back/undo; no publication, retries or cross-entity transaction.

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": {
      "page_id": "<page_id>",
      "changes": "<changes>",
      "expected_page_fingerprint": "<expected_page_fingerprint>",
      "expected_report_content_fingerprint": "<expected_report_content_fingerprint>"
    },
    "name": "groups_filters"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
dry_runNo
page_idYes
report_idNo
expected_page_fingerprintYes
expected_report_content_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the destructiveHint=true annotation it discloses the write mechanics: "Guarded journalled page write/read-back/undo; no publication, retries or cross-entity transaction." It also enumerates what is preserved (members, child-group links, controlStatePassThrough, geometry, child settings) and explicitly bounds its own guarantees ("no claim of full nested-group/blend traversal or effective runtime inheritance"), which is unusually candid.

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 purpose, then prerequisites and guarantees; nearly every clause carries information. It is dense with domain jargon (controlStatePassThrough, advisory direct-member compatibility) that costs some readability, but no sentence is filler.

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 destructive, multi-parameter, concurrency-guarded mutation with an output schema, this covers atomicity, preconditions, preserved state, and explicit limits. The main missing piece is the meaning of dry_run and its default of true, which materially affects whether an agent's call mutates anything.

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%, so the description must carry the load, and it largely does: it defines the changes item shape, the complete-list semantics of filter_ids with "[] clears," and the null/omitted = unchanged rule. Fingerprint parameters are tied to their sources (page_get, filters_list). Gaps remain: report_id, page_id, and especially dry_run=true by default (does the default mean no write occurs?) are not explained.

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?

"Set group filter IDs and/or inheritance in one page-atomic batch" states a specific verb (set), resource (group filters), and scope (single page, batched, atomic). The phrase "one page-atomic batch" distinguishes it from per-group or per-filter siblings without needing to name them.

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 gives real prerequisites: "Refresh viewer first; fingerprints from page_get and filters_list" and "Attached filter sources with matching draft/published required," which tells the agent exactly what must be true before calling. It stops short of naming when-not-to-use or an explicit alternative (e.g., page_filters or components_filters), so no exclusion guidance.

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