Skip to main content
Glama

Set my coaching brain rules

set_my_brain_rules
Idempotent

Use this when a Phorme coach describes how they coach and wants their coaching brain to follow it, for example "every session starts with mobility, main lifts stay in 3 to 6 reps, never two hard days in a row". Sent with the coach's words, it reads them into the brain's rules and saves nothing: it returns the rules, one plain line per rule, and what no rule covers yet. Sent with those rules and confirmation, it saves them, and Phorme checks the brain on sample members and says whether every plan still works. Members train by the saved rules from their next session. It needs a connected Phorme account that owns the brain; set confirmation to true only after the coach said yes to the rules as read back.

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": "set_my_brain_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoHow the coach coaches, in their own words from this conversation. Never invented. Sent to read a draft.
rulesNoThe rules a draft returned, unchanged or as the coach corrected them: method, voice, banned_phrases and share. Sent to save.
brain_idYesThe brain id from the coach's brains.
confirmationNoTrue only after the coach confirmed these rules. Needed to save.

Output Schema

NameRequiredDescriptionDefault
nextNo
saidNoOne plain line per rule the draft read: key and line.
brokeNoAfter a save that broke a plan: which sample and why.
rulesYes
savedYesFalse for a draft, true once saved.
unreadNoParts of the coach's words no rule covers yet.
brain_idYes
preview_okNoAfter a save: whether every sample member still gets a plan that works.
console_urlNo
requires_confirmationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / broke
      Added value: +{
      +  "description": "After a save that broke a plan: which sample and why.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: the read phase saves nothing and returns rules plus uncovered topics, the save phase requires confirmation and checks sample members, and saved rules affect the next session. It also states the need for a connected Phorme account that owns the brain. No contradiction with readOnlyHint=false, destructiveHint=false, or idempotentHint=true.

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 trigger is front-loaded and every sentence contributes workflow or return information. It is somewhat dense and long for a single paragraph, but the length is justified by the two-phase read/save behavior.

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?

Given the two-mode workflow, nested rules object, confirmation gating, and output schema, the description covers what an agent needs: account prerequisite, when to read, when to save, what gets returned, and downstream effect. Return value detail is not required because an output schema exists, yet the description still summarizes it usefully.

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 description coverage is 100%, so the schema already documents text, rules, brain_id, and confirmation. The description reinforces the read/save distinction and confirmation timing but adds little format or validation detail beyond the schema. Baseline 3 is appropriate.

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: reading coach-provided text into brain rules or saving confirmed rules. The two operating modes (draft read vs save) are made clear. It does not explicitly distinguish itself from nearby siblings such as set_my_coach_principles or teach_my_coach, so it falls short of a 5.

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?

Gives a clear trigger: use when a Phorme coach describes their coaching approach and wants the brain to follow it. It explains the read-first workflow and the confirmation condition before saving. It does not name alternative tools or explicit exclusions, so it is strong but not exhaustive.

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.