Skip to main content
Glama

send_advice_to_game

Send coaching advice into the player's in-game Coach panel so they see your next steps without leaving World of Warcraft. Use it to answer game questions and deliver follow-up actions in plain text.

Instructions

Show advice in the player's in-game Coach panel.

Use this to answer a question from questions_from_game (pass its question_id), and whenever you give the player new next steps, so they see them inside the game too. The player sees it after their next /reload (after a full game restart the first time), so also say your answer in the chat. Plain text only, no combat advice.

Args: title: A short heading, at most 80 characters, e.g. "Next steps". steps: The next 1-3 actions in order, one sentence each (at most 5, 300 characters each). character: Character name or "Name-Realm", case-insensitive. Leave empty for the most recently saved character. text: An optional short explanation (at most 4000 characters). warnings: Optional things to watch out for (at most 5). question_id: The id from questions_from_game when this answers a question. source: Who wrote it, shown in the panel, e.g. "Claude Code coach".

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": {
      "title": "<title>",
      "steps": "<steps>"
    },
    "name": "send_advice_to_game"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
stepsYes
titleYes
sourceNoyour AI coach
warningsNo
characterNo
question_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.10.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare it is a non-idempotent, non-destructive, non-open-world write; the description adds the crucial delivery semantics that annotations cannot express — the player only sees the advice after their next /reload (a full restart the first time) — plus the plain-text-only constraint. These are exactly the behavioral facts an agent needs before calling and before deciding what else to say.

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?

Purpose and usage come first, followed by a clean per-argument block, so it is well front-loaded and every section is scannable. It is slightly longer than needed — the parenthetical about full game restarts is awkwardly nested, and the steps limit is stated twice — but no sentence is filler given the empty schema descriptions.

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?

An output schema exists, so return values need no explanation, and the description covers everything else a seven-parameter write tool requires: triggers, delivery timing, content restrictions, and per-field limits. Nothing an agent needs in order to call this correctly 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?

With 0% schema description coverage, the description carries the full burden and mostly succeeds: it explains all seven parameters, including character name formatting and the empty-means-most-recent default, length caps for title/text, and the provenance role of question_id and source. The one blemish is the steps guidance, which says "1-3 actions" and then "at most 5", leaving the actual limit ambiguous.

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 opening sentence gives a specific verb and resource ("Show advice in the player's in-game Coach panel") and the body distinguishes it from the sibling read tool by naming questions_from_game and its question_id. An agent can tell this is the write-side delivery channel for coaching content without opening the schema.

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?

Explicit triggers are given: use it to answer a question from questions_from_game (passing that question_id) and whenever you hand the player new next steps. A boundary is also stated ("no combat advice"), and the "also say your answer in the chat" instruction prevents a misuse pattern where the agent assumes in-game delivery is sufficient.

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