Skip to main content
Glama

start_build_with_ai

Start an AI build (Coach Pro, spends AI credits, charged only if something is built): WORKOUT_TEMPLATE, DIET_TEMPLATE, CLIENT_WORKOUT_PLAN / CLIENT_DIET_PLAN (need clientId; loaded into an unsaved builder, not assigned), HABITS, CHECKIN_QUESTIONS, PROGRAM (no client is enrolled) or ONBOARDING_FORM (returned as data; the live form is unchanged). Check get_build_with_ai_status for the price first, then poll get_ai_build_job. (confirm-gated: previews until confirm: true)

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": {
      "input": "<input>"
    },
    "name": "start_build_with_ai"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes
confirmNoMust be true to actually execute. If false/omitted, returns a preview only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing cost semantics (spends AI credits, charged only if something is built) and the exact side effects per kind — plans land in an unsaved builder and are not assigned, PROGRAM enrolls no client, ONBOARDING_FORM is returned as data and leaves the live form unchanged. This resolves the main ambiguity an agent would have about a non-destructive write. Minor gap: no mention of latency or failure/retry behavior for a long-running generation.

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-loads the action and cost, then the per-kind effects, then the workflow. Dense parenthetical enumeration is justified by the eight distinct kinds, though the single-sentence block with nested parentheses is harder to scan than a short list would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a credit-spending, confirm-gated generation tool with no output schema, it supplies everything needed: cost model, side-effect per kind, confirm requirement, and the follow-up status tool for results. Nothing essential to a correct invocation is missing.

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?

Adds real meaning to the 'kind' enum by describing the outcome of each value, and explains the confirm gate and the clientId requirement for CLIENT_* kinds. The other optional fields (goal, level, weeks, daysPerWeek, caloriesPerDay, dietType, language, notes) are left entirely to the schema, which only covers 50% of parameters.

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 resource ('Start an AI build') and immediately enumerates the eight supported build kinds, so an agent knows exactly what is produced. It also names the two sibling tools involved in the flow, distinguishing this create action from status/job reads.

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?

Gives an explicit ordered workflow: call get_build_with_ai_status for the price first, then this tool, then poll get_ai_build_job. It also states the confirm-gating rule (preview until confirm: true), which is the key decision point before invoking.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.