Skip to main content
Glama

Record second-brain task event

second_brain_record_event

Append a redacted action, result, failure, verification, or checkpoint event to a task ledger to maintain traceable workflow records.

Instructions

Append one redacted action, result, failure, verification, or checkpoint event to the current task ledger.

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>",
      "eventType": "<eventType>"
    },
    "name": "second_brain_record_event"
  }
}

Input Schema

NameRequiredDescriptionDefault
eventNo
taskIdYes
eventTypeYes

Output Schema

NameRequiredDescriptionDefault
recordYes
taskIdYes
createdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description doesn't need to repeat safety. It does add two useful facts beyond the annotations: 'redacted' tells the caller the payload must be sanitized before writing, and 'Append one' reinforces that repeated calls accumulate rather than overwrite. It says nothing about task-state requirements or what a rejected append looks like.

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?

One sentence, front-loaded with the verb and the destination, with the allowable event kinds inline. Nothing redundant and nothing padded.

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

Completeness3/5

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

With an output schema present, return values needn't be explained, and annotations cover the safety profile. What remains missing is how to shape the nested 'event' payload and whether an active task is a hard precondition — material gaps for a non-idempotent append tool.

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 0%, so this is the only source of meaning for the three parameters. It only loosely maps them: 'current task ledger' hints taskId scopes the write, and the listed event kinds effectively document eventType better than the bare regex pattern does. The free-form 'event' object (additionalProperties: {}) — the parameter most in need of explanation — is left entirely undescribed.

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?

The description gives a specific verb and resource ('Append one ... event to the current task ledger') and enumerates the event kinds (action, result, failure, verification, checkpoint), so an agent knows exactly what gets written. It stops short of distinguishing this generic append from task-lifecycle siblings like second_brain_task_start/task_finish, which likely also write ledger entries.

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?

Usage is only implied: 'current task ledger' signals that an active task must exist, and 'one ... event' signals one event per call. There is no explicit statement of when to prefer this over task_start/task_finish or over capture, and no preconditions or exclusions are given.

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