Phorme Training

Ask my coach

ask_my_coach

Read-only

Use this when a Phorme coach wants to hear how their AI coach answers one question, to check it sounds like them. It returns the answer and the coach's own passages it drew on, and changes nothing. Each answer runs Phorme's model under a spending cap; once the cap is reached it says so. It needs a connected Phorme account that owns the brain.

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>",
      "question": "<question>"
    },
    "name": "ask_my_coach"
  }
}

Input Schema

Name	Required	Description	Default
`brain_id`	Yes	The brain id of the coach's own build, for example "cameron".
`question`	Yes

Output Schema

Name	Required	Description	Default
`answer`	Yes
`sources`	No
`brain_id`	No
`question`	No
`spent_usd`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses the spending cap and its failure message ('once the cap is reached it says so') and the prerequisite of a connected Phorme account that owns the brain. It also confirms the response shape (answer plus source passages) and the no-side-effect nature, which is exactly the extra context annotations cannot carry.

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?

Four short sentences, front-loaded with the usage condition, then behavior, limits, and prerequisites. 'It ... changes nothing' mildly restates the readOnlyHint annotation, but nothing else is wasted.

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?

With an output schema present the description need not detail return values, yet it still summarizes them. Auth prerequisites, spending-cap behavior, and the no-mutation guarantee cover everything an agent needs to invoke this correctly.

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

Parameters3/5

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

Schema coverage is 50%: brain_id is documented with an example, while question has only length constraints. The description adds real meaning by implying exactly one question per call and by tying brain_id to an account that owns the brain, but it gives no format guidance for question beyond that. Adequate, not compensating fully for the coverage gap.

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 concrete verb and resource ('hear how their AI coach answers one question'), the returned payload (answer plus the coach's own passages), and the intent (checking the coach sounds like them). That framing makes it clearly distinct from siblings like teach_my_coach, correct_my_coach, and get_my_coach without needing to open any schema.

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?

'Use this when a Phorme coach wants to hear how their AI coach answers one question, to check it sounds like them' gives a clear triggering condition and intent. It does not explicitly name the alternative tools (teach_my_coach, correct_my_coach) or state when not to use it, so it stops short of the top score.

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.