Metadata MCP Connector

Update Experiments Daily Budgets

update_experiments_daily_budgets

Destructive

Update daily budget allocations for one or more experiments in the Metadata platform.

            KEYWORDS: experiment, budget, daily, update, change, adjust, spending, allocation, modify

            WHEN TO USE:
            - User wants to "change the daily budget for experiment X"
            - User asks to "adjust daily budget for experiments A, B, C"
            - User requests to "update experiment budgets"
            - User wants to "allocate more budget to experiment Y"
            - User asks to "set daily budget to X for multiple experiments"

            PURPOSE:
            This tool allows you to adjust the daily budget amount for active experiments.
            The daily budget controls how much money each experiment can spend per day.

            REQUIRED PARAMETERS:
            - budgets: A dictionary mapping experiment IDs to their new daily budget values

            BUDGET VALUE FORMAT:
            Budget values can be provided as:
            - Strings with comma separator (European format): "100,50" → 100.50
            - Strings with dot separator (US format): "100.50" → 100.50
            - Numbers: 100, 100.5, 100.50
            - All values are automatically converted to 2 decimal places

            INPUT EXAMPLES:
            - Single experiment: {"budgets": {"12345": "100.50"}}
            - Multiple experiments: {"budgets": {"12345": 100.50, "12346": "150,75", "12347": 200}}

            INTEGRATION WITH OTHER TOOLS:
            - Use search_experiments to find the experiment IDs to update the daily budget.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`budgets`	Yes	Dictionary mapping experiment IDs to new daily budget values. Keys are experiment IDs (integers or strings), values are budget amounts (numbers or strings with comma/dot separators). Example: {'12345': 100.50, '12346': '150,75'}

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description aligns with them, adding genuinely non-obvious behavior: values can be European comma or US dot strings, and all values are normalized to 2 decimal places. It also says budgets apply to active experiments. It does not detail side effects or irreversibility, but the annotation coverage lowers the burden.

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 description is front-loaded with a clear one-sentence summary and then organized into labeled sections (WHEN TO USE, PURPOSE, FORMAT, EXAMPLES, INTEGRATION). The KEYWORDS section and the repeated PURPOSE sentence add some redundancy, but the structure and concrete examples keep it usable despite the length.

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 single-parameter mutation tool, the description covers when to use it, the input format, worked examples, and how to obtain experiment IDs via search_experiments. The main gaps are the absence of any indication of return behavior (no output schema) and what happens for inactive or unknown experiment IDs, but these are not blockers for a correct invocation.

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

Parameters5/5

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

The schema already documents the budgets dictionary at 100% coverage, but the description goes well beyond it by explaining European comma semantics ('100,50' -> 100.50), dot/US format, numeric inputs, automatic rounding to 2 decimals, and providing single- and multi-experiment examples. This adds real meaning that the schema pattern alone does not convey.

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 states a specific action ('Update daily budget allocations') on a specific resource ('experiments') and adds the scope 'one or more,' which separates it from broader experiment-management siblings like manage_experiment. The PURPOSE section reinforces the semantics without tautology, explaining that the daily budget controls per-day spend.

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?

The WHEN TO USE section provides concrete natural-language triggers ('change the daily budget for experiment X', 'set daily budget to X') that make matching easy. It also names search_experiments as the companion lookup tool. However, it does not explicitly state when not to use this tool or point to alternatives for non-budget experiment changes, so exclusions are missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Metadata MCP Connector tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?