Skip to main content
Glama

Blends Input Filters

blends_input_filters
Destructive

Replace or clear filter lists on up to 100 saved blend inputs in one report write, previewing changes first while preserving joins, fields and other input settings.

Instructions

Replace filter lists on 1-100 distinct saved blend inputs in one report write.

Use exact input_path and report fingerprint from blends_list. filter_ids is the complete list; [] clears it. Only saved filters belonging to the input datasource can be attached; source must be attached with matching draft and published definitions. Clearing does not require access to an old source. Preserves joins, fields, other input settings and consumers. Validates filters against native source schemas, not query execution. Preview by default; undo uses operation_restore. Does not edit or publish datasource assets.

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": "blends_input_filters"
  }
}

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

A4.5/5.0
Behavior5/5

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

Beyond the annotations it discloses the key semantics of a destructive operation: filter_ids is a complete replacement list with [] clearing, clearing circumvents old-source access requirements, joins/fields/other input settings/consumers are preserved, and validation uses native source schemas rather than query execution. It also states the preview-by-default behavior and the restore path, which is exactly the context an agent needs before a destructiveHint=true call.

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 action and scope come first, followed by prerequisites, semantics, and exclusions in a logical order with no filler. It is dense with semicolon-joined clauses that read somewhat like a spec dump, but nearly every clause carries operational information.

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 batch mutation with an output schema present, the description covers limits, preservation guarantees, validation basis, preview default, and rollback route. The remaining gap is report_id's null behavior and how the agent should construct the changes array, which matters given undocumented parameters.

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?

With 0% schema description coverage the description must carry the load, and it defines input_path sourcing, the fingerprint's origin, filter_ids' complete-list semantics including the empty-list case, and dry_run's default preview behavior. The blend_id field and the report_id null default are never addressed, and the changes array structure is only implied by the count constraint.

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?

The opening sentence names a specific verb and resource with scope: 'Replace filter lists on 1-100 distinct saved blend inputs in one report write.' It also draws a boundary against adjacent capabilities with 'Does not edit or publish datasource assets,' so an agent can separate it from datasource-editing siblings without opening a schema.

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 routes the agent to siblings for prerequisite values ('Use exact input_path and report fingerprint from blends_list') and for reversal ('undo uses operation_restore'), and it states that preview is the default. It gives no guidance on when to use this versus editing filter definitions themselves (filters_update_conditions), so the alternative selection is clear for setup and rollback but not for the broader task.

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