Skip to main content
Glama

Filters Update Conditions

filters_update_conditions
Destructive

Replace complete condition trees of saved filters by ID in one write, preserving datasource, bindings, and metadata while previewing affected charts and blend inputs.

Instructions

Replace complete condition trees of saved filters by ID in one resource write.

Each change has filter_id and tree (see filter_validate). Keeps the existing datasource, name, filter ID, bindings and opaque entry/value metadata. Replaces the entire filterDefinition and its format version, not individual leaves. Native validation requires an attached source with matching draft/published. Preview includes old/new definitions and exact saved references: changes can affect multiple charts and blend inputs. Source validation is not proof of every consumer query result. Journal, conflict preflight, full read-back and operation_restore; no automatic publication, detachment or mutation retry.

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": {
      "changes": "<changes>",
      "expected_report_content_fingerprint": "<expected_report_content_fingerprint>"
    },
    "name": "filters_update_conditions"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
dry_runNo
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 destructiveHint=true annotation, the description discloses what is preserved versus replaced, that replacement bumps the filterDefinition format version, that changes can ripple into multiple charts and blend inputs, and that source validation does not prove downstream query results. It also covers the operational envelope: journal entry, conflict preflight, full read-back, operation_restore recovery path, and the absence of automatic publication, detachment, or mutation retry.

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 destructive core action is front-loaded in the first sentence and the remaining sentences each contribute new operational facts rather than restating the schema. The closing sentence is telegraphic ("Journal, conflict preflight, full read-back and operation_restore;") and reads as compressed notes, costing a little clarity without much waste.

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 bulk mutation, the definition covers prerequisites, replacement scope, side-effect radius, and recovery, and the existence of an output schema relieves it of explaining return values. It is missing explicit guidance on the required fingerprint and on when preview (dry_run) applies, which are the two details an agent most needs before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, yet it only explains the shape of the required `changes` entries (filter_id plus tree). The other three parameters are never named: the required `expected_report_content_fingerprint` is only obliquely hinted at by "conflict preflight," and `dry_run` (preview) and `report_id` are not tied to their parameter names or defaults. An agent must open the schema to know what to supply for the required fingerprint, which is the riskiest omission.

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?

"Replace complete condition trees of saved filters by ID in one resource write" gives a specific verb (replace), a specific resource (saved filter condition trees), and explicit scope (whole trees, not leaves). This distinguishes it from filter_validate (referenced) and from creation/deletion siblings without needing their schemas.

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 names filter_validate as the place to learn the tree shape and states the prerequisite that native validation requires an attached source with matching draft/published state. It also clarifies what is not replaced (datasource, name, bindings, metadata) and that leaves are never edited individually, which implicitly steers away from partial-update expectations. It stops short of explicitly contrasting with filters_create/filters_delete or listing when not to use it.

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