saor-mcp

brain_feedback

Record outcomes and metrics to create a performance memory, enabling the AI brain to learn from successes and failures over time.

Instructions

Report an outcome back to the brain — what worked, what didn't, metrics. Creates a performance memory that helps the brain learn what's effective over time.

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": {
      "outcome": "<outcome>"
    },
    "name": "brain_feedback"
  }
}

Input Schema

Name	Required	Description
`metrics`	No	JSON string of metrics (e.g. '{"ctr": 0.12}')
`outcome`	Yes	What happened (e.g. 'high engagement', 'user confused by pricing')
`learnings`	No	What was learned from this outcome
`project_id`	No	Project/brain ID (optional if SAOR_PROJECT_ID is set)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.2.0Aug 2, 2026

TDQS

A3.6/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It does state that the tool 'Creates a performance memory' (a write operation), but it omits other relevant behavioral traits such as whether it overwrites existing memories, reversibility, or any permission requirements. The disclosure is minimal and partially implicit.

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?

The description is concise, consisting of two sentences that immediately convey the primary action and its purpose. Every phrase earns its place, with no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low complexity, 100% schema parameter coverage, and absence of an output schema, the description is mostly complete. It explains the tool's effect (creates a performance memory) and the schema details the inputs. The only notable gap is the lack of behavioral side-effect details, but this is partially addressed in the transparency dimension.

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?

The schema provides 100% coverage with clear descriptions for all four parameters (outcome, metrics, learnings, project_id). The description adds little beyond the schema, mentioning 'what worked, what didn't, metrics' which maps to outcome and metrics, but does not enhance understanding of the parameters' syntax or formatting.

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 description clearly states the tool's function with a specific verb ('Report') and resource ('the brain'), and differentiates it from siblings by noting it creates a 'performance memory' for learning. This distinguishes it from generic memory tools like brain_remember or brain_absorb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when reporting an outcome (what worked, what didn't, metrics), but it does not explicitly state when to use this tool versus alternatives like brain_remember or brain_context. No exclusions or alternative recommendations are provided.

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

Deploy Server