Skip to main content
Glama

Components Create

components_create
Destructive

Creates batches of native preset components on a loaded static page, validating drafts and the expected page fingerprint before a versioned write.

Instructions

Create a batch of native preset components on a loaded static page.

Use native_catalog for type/preset IDs and datasource_get for field names. Metrics require explicit aggregation using the source/editor enum, not a guessed default. Fields accept name or validated expression, plus optional display_name; aggregate expressions require AUTO (7). New components cannot retain concept_name from another component. Primary dimensions/metrics are supported; presets needing other bindings fail native validation. Composite/responsive creation is not yet supported. All drafts are validated before one versioned page write. Preview IDs are provisional. operation_restore removes the added components if no later changes conflict. Does not create datasource/report 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": {
      "page_id": "<page_id>",
      "new_components": "<new_components>",
      "expected_page_fingerprint": "<expected_page_fingerprint>"
    },
    "name": "components_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
page_idYes
report_idNo
new_componentsYes
expected_page_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.2/5.0
Behavior5/5

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

Without repeating the annotations, it discloses the write pipeline ('all drafts are validated before one versioned page write'), provisional preview IDs, the operation_restore undo path and its conflict caveat, and validation failures for non-primary bindings. That is substantially more than destructiveHint/readOnlyHint convey and is consistent with destructiveHint=true.

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?

Dense and front-loaded with constraints sequenced logically from prerequisites to validation to undo. A few sentences are cramped across line breaks and the metrics/aggregation rule requires careful parsing, but there is no filler.

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?

Output schema exists, so return values need no explanation, and the batch-write, validation, and restore semantics cover the risky behavior of a destructive tool. Missing is the meaning of the required expected_page_fingerprint guard and what dry_run does, which an agent needs before calling 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 0% schema description coverage the description carries the load, and it does real work: metrics require an explicit source/editor aggregation enum, aggregate expressions require AUTO (7), fields take a name or validated expression plus optional display_name, and concept_name cannot be retained from another component. Gaps remain: expected_page_fingerprint (required) is never explained as a concurrency token, and dry_run, page_id/report_id, and layout fields (top/left/width/height/rotation) go unmentioned.

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, and constraint set: 'Create a batch of native preset components on a loaded static page.' That is enough to distinguish it from components_patch, components_copy_to_page, and components_duplicate, though no sibling is named explicitly.

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 concrete prerequisites (use native_catalog for type/preset IDs, datasource_get for field names) and clear scope exclusions: no composite/responsive creation, no datasource/report assets, presets needing other bindings fail validation. It does not say when to prefer components_patch or components_duplicate over this tool, so the alternative-selection guidance is incomplete.

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