Skip to main content
Glama

Components Filters

components_filters
Destructive

Set saved filter bindings and inheritance on page components, with optional clearing, validation, and preview before applying changes.

Instructions

Set saved filter bindings and inheritance on components within one page.

Each change: component_id, optional filter_ids (complete ordered list; [] clears local bindings), optional inherit_filters. Omitted/null properties stay unchanged. Get fingerprints from page_get and filters_list; refresh the viewer before preparation. Native component-schema validation rejects incompatible filters; direct attached datasources with matching draft/published required. Does not create/delete resources or mutate viewer control selections. Page journal/read-back/undo also guard report resource changes. Not a cross- entity transaction or proof of query results. Page/group/report-level binding and blend datasets need their own operations. Preview by default; no publication.

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": "components_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

A4.8/5.0
Behavior5/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true, and the description builds on that by specifying what actually changes and can be lost: filter_ids is a complete ordered list where [] clears local bindings, omitted/null properties stay unchanged, and native schema validation rejects incompatible filters. It also discloses the concurrency safeguard ('Page journal/read-back/undo also guard report resource changes'), the draft/published matching requirement for directly attached datasources, and the dry-run default, which is far beyond what the annotations convey.

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 per-change semantics, preparation, validation, and non-goals — a sensible ordering where each line contributes information. The dense, telegraphic phrasing ('refresh the viewer before preparation') trades a little readability for compactness, but there is no filler.

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?

Given a destructive 6-parameter mutation with an output schema (so return values need not be described) and high complexity, the definition covers mutation semantics, validation failures, dry-run behavior, prerequisites, and explicit non-goals. Nothing essential for a correct first invocation is missing.

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 explains component_id, filter_ids ordering and empty-list semantics, inherit_filters null/omitted behavior, and points at page_get/filters_list as fingerprint sources. It falls short on report_id and on explicitly tying expected_page_fingerprint/expected_report_content_fingerprint to optimistic-concurrency failure, so one parameter remains fully undocumented.

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 with explicit scope: 'Set saved filter bindings and inheritance on components within one page.' It also delimits itself from siblings by naming that page/group/report-level binding and blend datasets require their own operations, so an agent can distinguish this from page_filters, groups_filters, report_filters and the blends tools.

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?

Gives concrete prerequisites ('Get fingerprints from page_get and filters_list; refresh the viewer before preparation') and explicit exclusions ('Does not create/delete resources or mutate viewer control selections', 'Not a cross-entity transaction', 'Preview by default; no publication'). When-not-to-use is stated as clearly as when-to-use.

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