Skip to main content
Glama

Components Patch

components_patch
Destructive

Patch existing components on a single report page in one versioned write with RFC 6902 operations and fingerprint checks; dry_run previews changes before applying.

Instructions

Patch existing components on ONE page in a single versioned write.

Each change identifies a component and RFC 6902 add/replace/remove/test operations relative to that component. Preserve all unknown fields. Use page_get's fingerprint. Geometry is in attributeConfig.componentAttribute; styles and bindings are in propertyConfig.componentProperty and conceptDefs. dry_run previews changes without a remote write. Returns a durable operation ID and read-back status. Does not change a component's ID or datasource.

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>",
      "changes": "<changes>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "components_patch"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
dry_runNo
page_idYes
report_idNo
expected_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 give readOnlyHint=false and destructiveHint=true, and the description adds real context on top: expected_fingerprint makes the write optimistic-concurrency guarded, 'remove' is one of the valid ops, dry_run defaults to a non-writing preview, unknown fields are preserved, and it explicitly states component ID and datasource are untouched. It does not cover permissions, partial-failure behavior, or whether a write can be rolled back, which keeps it from a 5.

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?

Front-loaded with scope and the core write model, then layered detail; nearly every line carries information an agent needs to build a patch. It is dense and jargon-heavy (attributeConfig/propertyConfig paths) but not padded.

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?

An output schema exists, yet the description still briefly notes the durable operation ID and read-back status, which is helpful. For a destructive, fingerprint-gated multi-change write it covers the essentials; the remaining gaps are report_id semantics and failure/partial-apply behavior.

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?

Schema description coverage is 0% for 5 parameters, so the description must compensate, and it largely does: 'changes' is explained as per-component RFC 6902 add/replace/remove/test operations relative to that component, and expected_fingerprint is tied to page_get. It also steers path construction by locating geometry in attributeConfig.componentAttribute and styles/bindings in propertyConfig.componentProperty and conceptDefs. Only report_id and page_id go unexplained.

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?

States a specific verb and resource ('Patch existing components') plus a hard scope limit ('on ONE page in a single versioned write'), which implicitly separates it from components_create, components_delete and components_arrange. It never names those siblings, so the differentiation is inferred rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Operational guidance is strong (use page_get's fingerprint, dry_run for preview, preserve unknown fields), which effectively tells the agent how to call it safely. However, it never says when to choose this over components_geometry, components_fields, components_switch_type or the other targeted component tools listed as siblings, so selection guidance is only implied.

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