Skip to main content
Glama

Blend Validate

blend_validate
Read-only

Validates a saved blend with the native detached runtime model, returning structural issue codes, runtime joins, and normalization paths to check report validity without saving or running queries.

Instructions

Validate a saved blend using the current native detached runtime model.

Returns native structural issue codes, runtime joins and normalization paths. Requires fresh saved/native report state; does not save or execute queries. Structural validity is not source/schema compatibility or feature availability. Use blend_join_types separately for the current Union flag. Non-left-deep trees remain visible in blend_get but this native validator rejects them. Optional rebuild_output_schema recomputes output fields on the detached model using current native source metadata and returns rebuilt_output_fields. Requires attached inputs with equal draft/published source definitions and source freshness checks. Does not save normalization or query the data.

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_id": "<blend_id>"
    },
    "name": "blend_validate"
  }
}

Input Schema

NameRequiredDescriptionDefault
blend_idYes
report_idNo
rebuild_output_schemaNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, and the description adds substantial context beyond that: it discloses that non-left-deep trees are rejected even though blend_get shows them, that rebuild_output_schema recomputes fields on the detached model and returns rebuilt_output_fields, and that inputs must be attached with matching draft/published definitions. The "does not save normalization or query the data" line reinforces the read-only profile with specifics rather than restating it.

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 core action is front-loaded and each sentence carries distinct information, but the prose is dense and repetitive, with "native" and "detached" recurring across sentences and no structural breaks to group the prerequisites versus the scope disclaimers.

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 validator with a documented output schema, this covers the major failure modes an agent needs to anticipate: stale report state, mismatched draft/published inputs, and unsupported tree shapes. The remaining gap is the meaning of the identifier parameters, which is nowhere explained.

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

Parameters3/5

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 parameter burden. It does well for rebuild_output_schema (explaining the recompute behavior and the rebuilt_output_fields result) and hints that report_id relates to saved/native report state, but blend_id and report_id remain largely undefined and the interaction between them is never stated.

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 ("Validate a saved blend") plus the model used ("native detached runtime model"), and the follow-up sentences bound the scope precisely: it does not save, does not execute queries, and does not assess source/schema compatibility. It also explicitly separates itself from blend_get (which still shows non-left-deep trees) and blend_join_types (which carries the Union flag).

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 states the preconditions for a meaningful call (fresh saved/native report state, attached inputs with equal draft/published definitions, source freshness checks) and routes two adjacent concerns to specific siblings. What it lacks is an explicit statement of when to prefer this validator over filter_validate or formula_validate, so the alternative-routing is partial rather than complete.

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