Skip to main content
Glama

Filters Delete

filters_delete
Destructive

Delete unreferenced saved filter resources by ID while preserving datasource and report assets. Preview changes by default and restore original IDs from the journal if needed.

Instructions

Delete unreferenced saved filter resources by ID, never datasource/report assets.

Get fingerprint and inspect exact saved references with filters_list. Rejects bindings on pages, nested/report components, blend inputs and unclassified exact references. No automatic detachment/cascade. Full definitions retained in the journal; operation_restore restores original IDs and registry ordering if no later edits conflict. Preflight/read-back is not a cross-entity lock against another editor adding references concurrently. Preview by default; no automatic publication or mutation retries.

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": {
      "filter_ids": "<filter_ids>",
      "expected_report_content_fingerprint": "<expected_report_content_fingerprint>"
    },
    "name": "filters_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
report_idNo
filter_idsYes
expected_report_content_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 declare destructiveHint=true and readOnlyHint=false; the description adds substantially more: no automatic detachment/cascade, full definitions retained in a journal with ID and ordering restoration, preview-by-default, no automatic publication or mutation retries, and an explicit warning that preflight/read-back is not a cross-entity lock. These are exactly the concurrency and reversibility facts an agent needs before invoking a destructive tool, and none of them contradict the annotations.

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 the core action and the scope restriction, then layered with preflight, cascade, restore and concurrency caveats in descending priority. It is dense and slightly telegraphic ('Rejects bindings on pages...'), but each sentence carries operational information rather than restating the name or schema.

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, journal-backed delete with an output schema (so return values need not be described), the definition covers safety, rejection rules, recovery and concurrency adequately. The main residual gap is the unexplained report_id parameter and the expected format of the fingerprint, which the agent must infer.

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; it explains the ID list ('by ID'), the fingerprint requirement (obtained via filters_list), and the preview behavior that maps to dry_run. The report_id parameter is never mentioned, leaving one of four parameters without meaning beyond its name.

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 ('Delete unreferenced saved filter resources by ID') and immediately scopes what it does NOT touch ('never datasource/report assets'), which separates it from the sibling delete tools for blends, components, pages and calculated fields. An agent can identify the target entity type without opening the 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?

Gives explicit prerequisites ('Get fingerprint and inspect exact saved references with filters_list'), explicit exclusions ('Rejects bindings on pages, nested/report components, blend inputs and unclassified exact references'), and the alternative path for recovery ('operation_restore restores original IDs'). This is a genuine when-to-use / when-not-to-use contract rather than implied usage.

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