Skip to main content
Glama

memory_record_task

Persist task outcomes with linked files, assumptions, evidence, and open risks so future sessions can retrieve context and avoid rework.

Instructions

Persist useful task outcomes with linked files, assumptions, evidence, and open risks for future sessions.

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": {
      "task": "<task>",
      "summary": "<summary>"
    },
    "name": "memory_record_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoAbsolute project root. Omit only where this session started; required elsewhere and on every subagent call.
taskYesTask or issue name.
filesNoFiles touched or relevant to the task.
formatNoReturn plain text or structured JSON. Default: text.
summaryYesWhat changed or was learned.
evidenceNoEvidence supporting the outcome.
open_risksNoRisks that remain unresolved.
supersedesNoPrevious memory IDs explicitly superseded; history is retained.
assumptionsNoAssumptions made during the task.
source_evidenceNoSource supporting this memory. Whole-file hashes are captured and rechecked on retrieval.
validation_refsNoValidation result artifact IDs; host-reported status is checked for current applicability.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.0
    • changedInput schema / properties / root / description
      Previous value: -"Absolute project root. Required with linked worktrees; subagents must pass their own worktree root on every call."New value: +"Absolute project root. Omit only where this session started; required elsewhere and on every subagent call."
  2. First observedv1.4.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description only adds the cross-session persistence intent. It does not disclose that repeated calls are non-idempotent and can create duplicate memories, nor does it explain the effect of supersedes on history, which is a meaningful behavioral gap for a write tool.

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?

A single well-formed sentence with the verb and core payload front-loaded and zero filler. The enumeration of field names mildly duplicates what the schema already lists, which keeps it just short of ideal.

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?

For an 11-parameter mutation tool, the description is thin: it omits duplicate-creation behavior, the meaning of supersedes for history, and any notion of the returned result (no output schema exists). The fully documented schema and safety annotations compensate for much of this, but an agent still learns little about consequences from the description alone.

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 coverage is 100%, with every parameter individually described including root's subagent requirement and source_evidence's hash rechecking, so the schema carries the semantic load. The description's field enumeration maps onto schema property names without adding syntax, format, or prioritization guidance, making the baseline 3 correct.

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?

States a specific verb ("persist") and resource ("task outcomes") and enumerates the payload categories it stores (files, assumptions, evidence, open risks). It is clearly distinguishable from read-oriented siblings like artifact_read, search, or grep, though it never explicitly names an alternative to contrast against.

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?

"For future sessions" implies the trigger point — recording outcomes so later sessions can recall them — but there is no explicit when-to-use/when-not or any routing to siblings such as task_pack (which likely produces the task context this tool records). Usage is inferable rather than stated.

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