Skip to main content
Glama

Finish second-brain task with reflection

second_brain_task_finish
Idempotent

Record a task’s outcome, verification, reflection, and optional lesson candidate; unverified results stay as candidates and cannot be promoted automatically.

Instructions

Append outcome, verification, reflection, and an optional lesson candidate. Unverified results remain candidates and cannot be promoted automatically.

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": {
      "taskId": "<taskId>",
      "outcome": "<outcome>",
      "reflection": "<reflection>"
    },
    "name": "second_brain_task_finish"
  }
}

Input Schema

NameRequiredDescriptionDefault
resultNo
sourceNo
taskIdYes
outcomeYes
nextChangeNo
reflectionYes
stopReasonNo
verificationNo
lessonCandidateNo

Output Schema

NameRequiredDescriptionDefault
recordYes
taskIdYes
createdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.7/5.0
Behavior3/5

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

Annotations already declare this is a non-destructive, idempotent write with no open-world access. The description earns credit for adding real semantics beyond that: unverified results stay as candidates and cannot be auto-promoted, which tells the agent about downstream consequences. It omits other useful behavior for a write tool — whether appends overwrite prior values, what happens to existing reflection/outcome fields, and how the verification object gates promotion.

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?

Two tight sentences with no filler, and the payload description is front-loaded before the caveat. Nothing is redundant, though the brevity comes at the cost of the specification gaps scored elsewhere rather than from deliberate restraint.

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

Completeness2/5

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 not be described. But for a 9-parameter mutation with two nested objects and zero schema documentation, the description leaves the agent without the field-level semantics or overwrite/promotion rules needed to call it correctly. It is materially under-specified for this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 9 parameters including two nested objects, so the description must carry the load and does not. It names outcome, verification, reflection, and lessonCandidate but gives no meaning, format, or constraints for taskId, result, source, nextChange, or stopReason, and never explains the errorSignature/lesson structure inside lessonCandidate. Names alone echo the schema without adding interpretation.

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

Purpose3/5

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

The description names the specific payload being recorded (outcome, verification, reflection, lesson candidate) but never states what the record is appended to or that it marks the task as finished — that framing only comes from the tool name and title. No sibling differentiation against second_brain_record_event or second_brain_upsert_card, which plausibly overlap. The purpose is inferable but not stated outright.

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

Usage Guidelines2/5

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

There is no when-to-use, when-not-to-use, or prerequisite guidance. The sentence about unverified results remaining candidates is a behavioral rule about promotion, not a usage signal telling the agent when to call this versus starting, capturing, or recording an event. An agent must guess the trigger condition.

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