Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

send_feedback

Opens a feedback card for the user to review, edit, and send themselves; use it to report missing capabilities or frustration without sending or attaching anything automatically.

Instructions

Open the Brilliant feedback card for the user to review and send. This does NOT send: the card opens, the user presses Send, and you tell them it is open and waiting (never claim it was sent). message is OPTIONAL (pre-fill a draft or open empty); attachments is tolerated but ignored (nothing about the user's world is ever attached). Feedback is a routing decision, not one surface, and consent scales with what leaves the machine: the user's words move by the user's act, the user's context moves only per-item opt-in, and your own observations ride telemetry, never GitHub or email. Offer it proactively, once and calmly (at most once per session AND once per class), when you hit a wall or a missing capability, when the user asks for something the product cannot do, or when the user is frustrated. Before running the routing flow (card vs GitHub issue vs email vs Discord), load the full playbook with get_knowledge(["reference/feedback"]).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "send_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageNoOPTIONAL. The drafted feedback message, in the user's own framing (the user can edit it before sending). Omit to open an empty card.
attachmentsNoIgnored in this version; accepted for backward compatibility (nothing about the user's world is ever attached).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false, so the safety bar is partly covered. The description still adds substantial non-schema behavior: the card is user-driven, nothing is actually sent, attachments are ignored, and a per-surface consent model governs what leaves the machine. It does not describe the return payload, but it does tell the agent what to report back ('open and waiting').

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?

Front-loaded with the crucial non-send warning, and every clause carries information rather than filler. The single dense paragraph mixes tool behavior with consent philosophy that arguably belongs in the referenced feedback playbook, which costs it a point.

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?

For a two-parameter, no-output-schema tool, the description covers what it does, what it does not do, when to offer it, how often, and where to get the routing playbook. An agent has everything needed to call it correctly and to report the outcome honestly.

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 both parameters are already documented, establishing a baseline of 3. The description adds genuine intent-level meaning beyond the schema — pre-fill 'in the user's own framing' and omit to open empty — and reinforces that attachments never carry user-world data.

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 specific verb and resource (open the Brilliant feedback card) and immediately scopes it by negating the likely misreading: 'This does NOT send.' That distinction is what separates it from any send/submit expectation an agent might otherwise form.

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?

Gives explicit triggering conditions (hit a wall, missing capability, request the product cannot do, user frustration), an explicit frequency cap (at most once per session AND once per class), and names the routing alternatives — card vs GitHub issue vs email vs Discord — with the get_knowledge prerequisite for the full playbook.

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