Skip to main content
Glama

Metis — Record Decision

record_decision

Save a standing user preference or decision so Metis recalls it in future requests and personalizes responses instead of asking again.

Instructions

Record a user preference or decision so Metis adapts to the user over time.

Use this whenever the user states (or confirms) a standing preference or makes a
decision worth remembering — coding style, citation format, a methods default, an
article/dataset they keep returning to, a naming convention, a workflow choice.
These are recalled into context on future requests (recall_decisions), so Metis
personalizes instead of asking again.

Args:
    decision: the preference/decision in plain language (e.g. "Always use tidyverse style in R, never base apply").
    category: preference | coding | citation | methodology | writing | article-ref | dataset | routing | other.
    context: optional — when/why it applies (e.g. "for the spatial analyses").
    scope: 'always' (persist) or 'once'.
    agent_slug: the specialist that should APPLY this decision — e.g.
        "frontend-designer-builder" for a layout rule, "writing-partner" for
        a prose rule, "librarian" for what matters in the library. Leave
        empty for a project-wide rule that every agent should carry.

        Attribution is what makes the decision reachable. `get_agent_context`
        injects an agent's own decisions plus the project-wide ones, and a
        flat list of every preference injected into every agent is noise that
        gets ignored. Measured 2026-08-24: user_decisions held 2 rows while
        session summaries held 7,578 decision entries — so invoking a
        specialist returned a persona and nothing about how the researcher
        wants things done, which is why routing to one stopped being worth it.

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": {
      "decision": "<decision>"
    },
    "name": "record_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoalways
contextNo
categoryNopreference
decisionYes
agent_slugNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.5
    • addedInput schema / properties / agent_slug
      Added value: +{
      +  "default": "",
      +  "title": "Agent Slug",
      +  "type": "string"
      +}
  2. Addedv0.1.4

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses persistence semantics ("recalled into context on future requests"), contrasts scope 'always' persist vs 'once', and explains the downstream injection behavior of agent_slug into get_agent_context. The measured note about 2 user_decisions rows versus 7,578 session-summary entries documents a real failure mode rather than restating mechanics.

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?

Purpose and trigger come first, then a clean Args block, so it is well front-loaded. The closing agent_slug rationale is over-long: the 2026-08-24 measurement and the editorial aside about routing becoming "no longer worth it" read as justification for the design rather than guidance the agent needs to fill the field.

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

Completeness5/5

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 are correctly left out, and all five parameters are covered with more meaning than the schema provides. Persistence and retrieval behavior are both explained, leaving nothing an agent needs in order to call this correctly.

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% and the schema has zero enums, but the description supplies the missing controlled vocabulary for category (nine values) and scope ('always' vs 'once') and gives a worked example for decision. agent_slug gets the richest treatment, including what to pass for specific specialists and what empty means, which no schema field communicates.

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 concrete verb+resource ("Record a user preference or decision") and frames the outcome ("so Metis adapts to the user over time"), which separates it from finding- or memory-oriented siblings. It names recall_decisions as the read counterpart but never contrasts itself with near neighbors like remember, commit_session_decisions, or record_routing_preference.

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

Usage Guidelines5/5

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

Gives an explicit trigger condition ("whenever the user states (or confirms) a standing preference or makes a decision worth remembering") plus five concrete qualifying examples spanning coding style, citation format, and workflow choice. The "standing"/"worth remembering" qualifier also implicitly excludes trivia.

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