Phorme Training

Rate my coach

rate_my_coach

Use this when a Phorme coach wants to score whether their AI coach sounds like them. Sent with 1 to 20 real student questions, it answers each (Phorme's model, under a spending cap) and returns a round. Sent with that round_id and one mark per answer (true if it sounds like the coach), with confirmation, it saves the score. Show the coach every answer before they mark it; never mark for them.

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": {
      "brain_id": "<brain_id>"
    },
    "name": "rate_my_coach"
  }
}

Input Schema

Name	Required	Description
`marks`	No	One per answer, in order: true if it sounds like the coach.
`brain_id`	Yes	The brain id of the coach's own build, for example "cameron".
`round_id`	No	The round to score. Sent with marks.
`questions`	No	Real student questions. Sent to start a round.
`confirmation`	No	True only after the coach marked every answer themselves. Needed to save marks.

Output Schema

Name	Required	Description	Default
`of`	No
`next`	No
`rated`	Yes
`answers`	No
`brain_id`	No
`round_id`	No
`spent_usd`	No
`sounds_like`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations (which only say non-readonly, non-destructive, closed-world), the description discloses meaningful behavior: answers come from Phorme's model under a spending cap, the first call returns a round, and saving requires an explicit confirmation. It does not say what happens on a re-score or whether rounds are immutable, but the key behavioral traits are covered.

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?

It is front-loaded with the trigger condition and then walks through mode one and mode two in order, with no filler sentences. It is slightly longer than needed, since some of the mode mechanics restate the schema's parameter descriptions.

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 dual-mode mutation tool with rich schemas and an output schema, the description supplies the mode-routing and confirmation gating an agent needs to call it correctly. It omits edge cases such as what happens if marks length mismatches answers or whether a round can be rescored, which keeps it short of 5.

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 coverage is 100%, so the baseline is 3; the description earns a 4 by tying parameters to modes (1–20 questions start a round; round_id plus one mark per answer plus confirmation saves), reinforcing the ordering requirement already in the schema.

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 description names a specific resource (the coach's AI-brain scoring round) and a specific action (rate/score how much the AI coach sounds like the coach), and it disambiguates the two operating modes (start a round vs. save marks). It is clearly distinct from siblings such as teach_my_coach or correct_my_coach, which modify the brain rather than score it.

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?

It explicitly states when to use it ("when a Phorme coach wants to score whether their AI coach sounds like them") and gives concrete workflow conditions for each mode, plus a hard rule not to mark on the coach's behalf. It does not name alternative tools or exclusion conditions, which keeps it at 4 rather than 5.

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

All Phorme Training 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.