Skip to main content
Glama

Blends Joins

blends_joins
Destructive

Update join types and key pairs on up to 100 saved Data Studio blend nodes, with preview-by-default changes and reversible writes.

Instructions

Change merge types/key pairs on 1-100 distinct saved blend nodes.

Use exact join_path and fingerprint from blends_list. key_pairs omitted preserves existing keys; Cross explicitly removes conditions. Non-cross merges need keys; provide them when converting from Cross. Pair names are input concept IDs (not output labels), as shown by blend_validate/blend_get. Union requires the current native feature flag. Source draft/published equality and native structural candidate validation precede a single guarded report write. Unknown unrelated fields and all input/output fields survive. No query-result or cross-source type-compatibility guarantee. Preview by default; applied changes are reversible through operation_restore.

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_joins"
  }
}

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

A4.7/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description goes well beyond by disclosing that validation runs before a single guarded report write, that draft/published equality is enforced, that unrelated fields and all input/output fields survive, and that changes are reversible through operation_restore. The default-preview behavior and the guarded atomic write are exactly the mutation traits an agent needs and cannot get from 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?

The most important constraint (exact join_path/fingerprint, scope limit) is front-loaded, and every line carries distinct constraints with no filler. The telegraphic fragment style is dense and slightly harder to parse than flowing prose, but nothing is redundant.

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 nested, multi-node mutation tool with an output schema, the description covers validation ordering, atomicity, reversibility, feature-flag gating, and field preservation, so an agent can call it safely. The remaining gap is the unexplained report_id and what the "guarded report write" actually targets.

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 carries heavy lifting and largely succeeds: it explains key_pairs null-vs-present semantics, that pair names are input concept IDs rather than output labels, that join_path must be exact from blends_list, and the 1-100 distinct-node bound. It leaves report_id entirely unexplained and only implies that expected_report_content_fingerprint comes from blends_list, so it is strong but not complete.

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?

"Change merge types/key pairs on 1-100 distinct saved blend nodes" gives a specific verb (change), a specific resource (merge type/key pairs on saved blend nodes), and a bounded scope (1-100 distinct nodes). This is clearly distinguishable from read-side siblings like blends_list and blend_get, which the description also references as the source of join_path and fingerprint.

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?

It states prerequisites (join_path and fingerprint must come exactly from blends_list; Union requires the current native feature flag), per-case rules (key_pairs omitted preserves existing keys, Cross removes conditions, non-cross merges require keys), and the recovery path (preview by default, reversible via operation_restore). It also names a boundary condition: no query-result or cross-source type-compatibility guarantee.

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