Phorme Training

Correct my coach

correct_my_coach

Use this when a Phorme coach reads an answer their AI coach gave and says how they would say it instead. It keeps the coach's version; every later answer that finds this question leads with it. Send the question, the answer unchanged and the coach's own fix. Set confirmation to true only after the coach approved the fix as written.

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>",
      "answer": "<answer>",
      "fix": "<fix>",
      "confirmation": "<confirmation>"
    },
    "name": "correct_my_coach"
  }
}

Input Schema

Name	Required	Description
`fix`	Yes	How the coach would say it, in their own words.
`answer`	Yes
`brain_id`	Yes	The brain id of the coach's own build, for example "cameron".
`question`	Yes
`confirmation`	Yes	True only after the coach approved this fix.

Output Schema

Name	Required	Description	Default
`kept`	Yes
`next`	No
`brain_id`	No
`corrections`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only say readOnly=false, destructive=false, openWorld=false, so the description has to carry the weight of disclosure. It does: it discloses the persistence semantics (the coach's version replaces future answers to this question) which is the key side effect. It does not say whether an existing correction can be overwritten or reverted later.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, zero filler, and the trigger condition is front-loaded in the opening clause. Each sentence has a distinct job: when to use, what it does, what to send, and the confirmation condition.

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?

All five parameters are required and enumerable from schema plus prose, and an output schema exists so return values need no description. The trigger plus the persistence effect plus the confirmation gate cover what an agent needs to invoke it correctly.

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 60%; the description compensates by naming the question, the answer and the fix, and by adding meaning the schema lacks: the answer must be sent 'unchanged' while the fix is the coach's own wording. It also states the confirmation gate in prose. Only brain_id goes unexplained in the description, and it is covered by the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (record the coach's own rewrite of an AI answer) and explains the downstream effect: 'every later answer that finds this question leads with it.' That effect is what really pins the tool down. It stops short of naming the confusable siblings (teach_my_coach, set_my_coach_principles, rate_my_coach), so the agent still has to infer the boundary.

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 reads an answer their AI coach gave and says how they would say it instead' gives a concrete trigger scenario. The sequencing rule for confirmation ('only after the coach approved the fix as written') adds a real usage gate. No explicit exclusion against similar sibling tools, though.

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.