Skip to main content
Glama

Metis · Memory Curator — Commit Session Decisions

commit_session_decisions

Record concrete session decisions to permanent memory at the end of every agent-routed session, ensuring key choices are captured for future retrieval.

Instructions

Commit key decisions from this session to permanent memory.

This is the mandatory recording checkpoint — call it at the end of every
agent-routed session, before delivering the final result to the user.
Unlike save_session_summary (which accepts any summary), this tool enforces
that at least one concrete decision is captured, and writes each decision
separately to episodic_memory for future retrieval.

Args:
    decisions: 1-5 plain-English decisions made this session. Be specific:
        "Chose logistic regression over mixed model due to data sparsity in
        Zone de Santé X" not "made a modelling decision".
    summary: 1-3 sentence summary of the session context (optional but useful).
    key_topics: Topic tags e.g. ["REDCap", "domain surveillance", "form design"].
    session_id: Optional session identifier.

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": {
      "decisions": "<decisions>"
    },
    "name": "commit_session_decisions"
  }
}

Input Schema

NameRequiredDescriptionDefault
summaryNo
decisionsYes
key_topicsNo
session_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the mandatory-checkpoint behavior, the enforcement constraint (at least one concrete decision required), and the storage destination (episodic_memory, permanent). It does not cover what happens on re-invocation, whether decisions are deduplicated, or the failure mode when the enforcement rule is violated.

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?

Front-loaded with purpose in the first sentence, followed by the timing directive, the sibling contrast, then a compact Args block. Every sentence earns its place — the example and constraint details are functional, not filler.

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?

For a 4-parameter mutation tool with no annotations and no output schema, the description supplies purpose, timing, enforcement behavior, storage target, and full parameter semantics. Remaining gaps are idempotency/duplicate-handling and error behavior, which an agent might need before calling twice.

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

Parameters5/5

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

Schema coverage is 0%, so the description must compensate and it does: all four parameters are explained, including the 1-5 decision count bound, the 1-3 sentence summary guidance, optionality markers, and a concrete specificity example contrasting a good decision string with a bad one. This adds real meaning beyond the bare JSON types.

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?

First line states a specific verb and resource: commit key decisions from this session to permanent memory. It explicitly distinguishes itself from save_session_summary (which accepts any summary) and specifies that each decision is written separately to episodic_memory, so an agent can tell it apart from sibling memory-writing tools without opening the schema.

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

Usage Guidelines4/5

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

Provides explicit timing guidance ("mandatory recording checkpoint — call it at the end of every agent-routed session, before delivering the final result") and names one alternative plus the condition that selects it. It stops short of addressing other decision-capture siblings such as record_decision or promote_session_decisions, so the routing picture is not fully complete.

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

Deploy Server

Other Tools