Skip to main content
Glama

Bundle Contracts

bundle_contracts
Read-only

Checks native bundle contracts against the loaded editor and reports resolved, changed, or untestable signatures, so you can fix NATIVE_CONTRACT_FAILED failures and know which signature to update.

Instructions

Check every native capability the MCP relies on against the loaded editor.

Data Studio's minified bundle renames members on each release. Tools resolve them by behaviour at call time; this reports, per contract, ok (with the name it resolved to), changed (with the reason) or not_testable (no live object of that kind in this report). Run it first when a tool fails with NATIVE_CONTRACT_FAILED or *_CONTRACT_CHANGED: a changed entry names exactly which signature in bundle.py must be updated. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "bundle_contracts"
  }
}

Input Schema

NameRequiredDescriptionDefault
report_idNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, and 'Read-only' merely restates that. The genuinely additive content is the per-contract tri-state result semantics (ok with resolved name, changed with reason, not_testable when no live object exists), which goes beyond the annotations. However, an output schema exists and carries the return shape, so most of that detail is duplicated rather than adding new behavioral disclosure.

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 the purpose, then the mechanism, then the failure trigger — a sensible order with little waste. The trailing 'Read-only.' duplicates the readOnlyHint annotation and could be dropped.

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?

Given an output schema exists, the description need not explain return structure, and it does cover purpose, mechanism, and the recovery workflow. The single gap is the undocumented report_id parameter, which leaves a small but real hole in an otherwise self-sufficient definition.

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?

The tool has one parameter, report_id, with 0% schema description coverage, and the description never mentions it. An agent cannot tell from the text what a report_id is for, whether it selects a prior diagnostic run, or how to obtain one — the one place where low coverage had to be compensated and wasn't.

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?

States a specific verb and object — 'Check every native capability the MCP relies on against the loaded editor' — and immediately explains the mechanism (bundle minification renames members, resolution is by behaviour at call time). This is clearly unlike any sibling in the catalog, which are all report/component/data operations.

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 an explicit trigger: 'Run it first when a tool fails with NATIVE_CONTRACT_FAILED or *_CONTRACT_CHANGED', plus the payoff (a changed entry names the signature in bundle.py to update). No when-not-to-use guidance or alternative diagnostic paths are stated, so it stops short of 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