Skip to main content
Glama

Configure how a shared space reconciles conflicting sources

set_reconcile_policy

Configure conflict resolution for shared spaces with multiple contributors: choose recency, authority, or human review modes. Set source ranks to flag contradictory facts instead of overwriting.

Instructions

Configure how a SHARED space resolves conflicts between DIFFERENT contributors (sources). A shared space is any space (e.g. user_id='org:acme') that multiple agents/people write to with a source on each remember. Modes: • RECENCY — newer assertion wins (default; contributors equally trusted). • AUTHORITY — a higher-ranked source wins; a lower-ranked source contradicting it is FLAGGED, not overwritten. Pass authority as {source: rank} (higher = more authoritative). • REVIEW — any cross-source conflict is FLAGGED for a human. A source correcting its OWN earlier fact always supersedes, regardless of mode.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "set_reconcile_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoRECENCY
run_idNo
user_idNodefault
agent_idNo
authorityNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the conflict-resolution semantics: lower-ranked sources are FLAGGED rather than overwritten in AUTHORITY mode, and a source correcting its own earlier fact always supersedes regardless of mode. Annotations only say readOnlyHint=false and destructiveHint=false, so this adds real behavioral context. It still omits whether a policy change applies retroactively to already-flagged conflicts, and whether special permissions are needed.

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 the scope statement, then a compact bulleted enumeration of modes where each bullet carries distinct information. No filler or restatement of the title; the parenthetical clarifications are brief and useful.

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?

An output schema exists, so return values need not be described, and the mode semantics are unusually well covered for a policy tool. The remaining gap is the three identity/routing parameters and the effect of changing policy on existing state, which an agent would want before invoking.

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 the description must carry the load, and it only partially does. It thoroughly explains `mode` (three named values with semantics) and `authority` as {source: rank}, but says nothing about `run_id`, `agent_id`, or the exact role of `user_id` beyond being an example of a shared-space identifier.

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?

States a specific verb ('Configure') and a precisely scoped resource ('how a SHARED space resolves conflicts between DIFFERENT contributors'), and defines what a shared space is with a concrete example (user_id='org:acme'). This cleanly separates it from the read-side sibling get_reconcile_policy without needing to name it.

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?

Gives strong decision guidance for choosing among the three modes, including which is the default (RECENCY) and what each does to conflicting facts (overwrite vs. FLAG). It does not, however, state when an agent should call this tool at all versus inspecting an existing policy or recording memories, so routing guidance is implied rather than explicit.

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