Skip to main content
Glama

Report Patch

report_patch
Destructive

Apply RFC 6902 patch operations to report content for edits no typed tool covers, with dry-run preview, journalled write, read-back verification, and restore.

Instructions

RFC 6902 operations on report_content_get's content, for anything no typed tool covers. Paths are relative to that content (/attributeConfig/reportAttribute/..., /propertyConfig/reportProperty/..., /resource/...). Prefer settings_set: it applies the editor's own rules. One journalled write; read-back; 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": {
      "patches": "<patches>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "report_patch"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
patchesYes
report_idNo
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description's main added value is the recoverability story: a single journalled write, a read-back, and operation_restore as an undo path. That is genuine context, but critical behavioural facts are unstated - notably that dry_run defaults to true, and what expected_fingerprint enforcement does on conflict (reject vs. overwrite), which is exactly the risk an agent needs to understand before a destructive patch.

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 and dense, with the most decision-critical clause ('Prefer settings_set') placed early and no filler. The closing telegraphic fragment ('One journalled write; read-back; operation_restore') is efficient but clipped enough to read as shorthand rather than a sentence.

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 values need no explanation, and the destructive-write profile is partly covered by annotations. But for a high-risk patch tool with a required fingerprint parameter and a dry_run default, omitting those two parameters entirely leaves a real gap an agent must close by reading the raw schema.

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

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters, so the description must carry the load and largely does not: dry_run and expected_fingerprint are never mentioned, and the patches array's op/value semantics are left entirely to general RFC 6902 knowledge. The one real contribution is clarifying that patch paths are relative to report_content_get's content with concrete path roots, which is useful but covers only part of one parameter.

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?

Names a precise verb and mechanism (RFC 6902 operations) on a precisely named target (report_content_get's content) and scopes it to gaps not covered by typed tools. The example path roots (/attributeConfig/reportAttribute/..., /propertyConfig/reportProperty/..., /resource/...) make the resource unmistakable and separate it from components_patch and navigation_patch.

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?

Explicitly frames itself as the fallback for 'anything no typed tool covers' and names the preferred alternative plus the reason ('Prefer settings_set: it applies the editor's own rules'). An agent knows both when to reach for it and when to route elsewhere without opening the schema.

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