Skip to main content
Glama

Blend Create

blend_create

Create a blended datasource from 2–5 attached report tables by defining joins, join keys, dimensions, and metrics so charts can query combined output fields.

Instructions

Create a blend (Resource > Manage blends > Add a blend).

blend: {name, tables: [{datasource_id, dimensions: [field names], metrics: [{name, aggregation?}]}] (2-5 tables attached to the report, fields from datasource_get), joins: one per table after the first, in order: {join_type (LEFT_OUTER_JOIN default, INNER_JOIN, RIGHT_OUTER_JOIN, FULL_OUTER_JOIN, CROSS_JOIN, UNION), keys: [{left_table (earlier table index), left_field, right_field}]}} - key fields must be listed as dimensions. Output fields are built by the editor's own blend schema builder. Fingerprint from blends_list. Result blend_id is the datasource ID for components_create; output field names are what charts use. Input datasources need their schema loaded in the editor (SCHEMA_NOT_READY: use one in any chart first, or report_refresh). Table names, input filters and the date range dimension are set afterwards with blends_inputs_rename / blends_input_filters. One journalled report write, restorable with 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": {
      "blend": "<blend>",
      "expected_report_content_fingerprint": "<expected_report_content_fingerprint>"
    },
    "name": "blend_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
blendYes
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

A3.8/5.0
Behavior4/5

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

Annotations only say non-read-only and non-destructive; the description adds materially more — that this is a single journalled report write restorable via operation_restore, and that the call can fail with SCHEMA_NOT_READY. The significant omission is that dry_run defaults to true in the schema but is never mentioned, so an agent could believe it created a blend when it only simulated one.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense run-on prose with nested braces and no line breaks or bullet structure, which makes it slow to scan for a schema this deep. The information is mostly non-redundant, but the mid-paragraph placement of the critical SCHEMA_NOT_READY prerequisite and the tail-end notes about post-creation editing bury important guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation isn't required, and the description already covers the downstream use of blend_id well. However, for a nested mutation tool with a dry-run default and a required concurrency fingerprint, failing to define dry_run and report_id leaves a real gap in what an agent needs to call it correctly.

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 schema description coverage reported at 0%, the description carries the burden and largely meets it: it explains the blend shape, the 2-5 table limit, that joins are one-per-table-after-the-first and ordered, the join_type default and allowed values, that left_table is an index of an earlier table, and the constraint that key fields must also be listed as dimensions. It leaves expected_report_content_fingerprint (beyond 'from blends_list'), report_id, and dry_run undefined.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ('Create a blend') plus a UI path for disambiguation. It also names the related tools it consumes and feeds (blends_list for the fingerprint, components_create for the resulting blend_id), which separates it from read-side siblings, though it never explicitly routes to blend_validate as a pre-check.

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?

Gives real operational context: the prerequisite that input datasources must have their schema loaded, the SCHEMA_NOT_READY failure and its two remedies (use in a chart first, or report_refresh), and which tools to use afterwards for table names, input filters and date range. It stops short of an explicit when-not-to-use or a stated alternative for validation, so not a 5.

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