Skip to main content
Glama

Memory conflict check

wever_memory-conflict-check
Read-only

Agent Memory: submit a memory update flow: the rule for a new fact that contradicts a remembered one (when the contradiction is noticed: as the new fact is written, only when both are read, or never; which fact wins: what the principal stated over what was observed, inferred or imported, the principal decides, the newest, the oldest, or both stay; whether the principal is asked, told, only logged or not told; and whether the old fact is retired with its date, kept and marked superseded, deleted or kept as if current), plus optionally the contradictions seen, each with its subject, the old and new facts and their sources, which fact the agent now acts on, whether the principal heard and whether the old fact was retired. The signed report says which fact wins, whether the contradiction reaches the principal and whether the stale version is retired or silently kept, and names a contradiction never noticed, both facts kept, the oldest fact winning, the old fact kept as if current and, among the contradictions seen, every older fact that won, every pair left both current, every inference that replaced what the principal stated and every old fact left unretired, then noticing only on read, a principal not told, a deleted old fact with no trail and the newest fact always winning, with the fix for each. This reads contradictions between remembered facts: cached context that outlives a change at its source is wever_cache-staleness-check, where each memory came from is wever_memory-provenance-check and the agent’s view checked against the system’s record after an interruption is wever_state-reconciliation-check. Verdict stale_facts_win, conflict_gaps, conflict_unverified or conflicts_resolved. POST /api/memory-conflict-check. Reads only the material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write. Paid URL: 0.10 USDC per call on Base via x402 exact, with the shared 10 signed-wallet free calls per rolling 30 days. Bind X-Wever-Wallet-Proof to the exact JSON arguments and the tool route. Returns a report with an Ed25519 signed receipt. Contract: /api/agent-memory-contract. Human page: https://weverlabs.com/agent-memory/.

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": "wever_memory-conflict-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
flowNoThe memory update flow, such as preference updates.
ruleNo
labelNoOptional name recorded in the report.
conflictsNoContradictions seen, with which fact won.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations: it states the tool 'Reads only the material in the call: no network request, fetch, money movement... or external write,' discloses pricing (0.10 USDC per call on Base via x402 exact) and a free-call allowance, and specifies the auth binding (X-Wever-Wallet-Proof bound to the exact JSON arguments and the tool route). It also discloses that a report with an Ed25519 signed receipt is returned and enumerates the verdict set.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first clause, and the long enumeration of report contents is defensible because no output schema exists. However, it is a single sprawling run-on paragraph that re-lists enum values already in the schema ('retired with its date, kept and marked superseded, deleted or kept as if current') and buries the pricing/auth details mid-paragraph.

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?

With no output schema, the description carries the return-value burden and does so: it names the verdicts (stale_facts_win, conflict_gaps, conflict_unverified, conflicts_resolved), describes what the signed report asserts, and specifies the endpoint and auth header. What remains thin is the per-conflict 'id' semantics and pagination/response shape details, which are minor for a check-style 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 75% and the schema already explains the rule enums and conflict fields in detail; the description restates those same enum meanings in prose ('when the contradiction is noticed... which fact wins... whether the old fact is retired') without adding new semantics. For the undocumented remainder of the schema, notably what 'id' on each conflict identifies, the description offers no extra meaning. Baseline 3 is appropriate.

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?

The opening clause names a specific verb and resource: 'submit a memory update flow' covering the contradiction rule (detect timing, winner, surfacing, stale handling) plus optionally observed conflicts. It then explicitly partitions the domain against three named siblings (cache-staleness-check, provenance-check, state-reconciliation-check), so an agent can distinguish it without opening schemas.

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?

Routing is explicit: 'cached context that outlives a change at its source is wever_cache-staleness-check, where each memory came from is wever_memory-provenance-check and the agent's view checked against the system's record after an interruption is wever_state-reconciliation-check.' That gives clear alternatives and an implicit boundary, though it never states a positive trigger condition (e.g. 'call this before writing a fact that may overwrite an existing preference').

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources