Skip to main content
Glama

Knowledge conflict check

wever_knowledge-conflict-check
Read-only

Agent Knowledge: submit a set of knowledge entries and the rule for settling contradictions: each entry with its id, the subject it is about (such as refund window), what it says, where it applies, when it was recorded, the period it applies to, its source, its priority and whether it is retired; and the rule (the newest entry wins, the highest priority wins, the higher-ranked source wins with the source rank, a person reviews it, or no rule). The signed report pairs every two entries on one subject that say different things, tells a real contradiction from entries about different scopes, entries about periods that do not overlap and pairs already settled by a retired entry, settles each contradiction by the recorded rule where its dates, priorities or source rank can decide it, and names contradictions on the same fact that no recorded rule settles, with what the rule would need to decide them; then entries the rule sets aside that are still served and a rule of none, with the fix for each. Values agree when they read alike without case, spacing or punctuation or state the same figures in the same words, and an entry with no scope applies everywhere. How an agent memory store handles a new fact against a remembered one is wever_memory-conflict-check and two versions of one policy text are wever_terms-change-check. Verdict contradictions_unresolved, consistency_gaps, consistency_unverified or entries_consistent. POST /api/knowledge-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-knowledge-contract. Human page: https://weverlabs.com/agent-knowledge/.

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": {
      "entries": "<entries>"
    },
    "name": "wever_knowledge-conflict-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
ruleNo
labelNoOptional name recorded in the report.
entriesYesEach knowledge entry.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the read-only, non-destructive, closed-world profile; the description adds real value beyond them: no network/fetch/message/external write, exact pricing path (0.10 USDC on Base via x402, 10 signed-wallet free calls per 30 days), the X-Wever-Wallet-Proof binding to exact JSON arguments and route, and an Ed25519 signed receipt. It does not explain why the call is non-idempotent (idempotentHint=false), which would have been useful for a tool returning signed receipts.

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?

Purpose is front-loaded, but the body is one dense semicolon-chained run-on covering report logic, equality semantics, sibling routing, safety, pricing and auth in a single block. The report-behavior sentence in particular is very hard to parse on first read and would benefit from splitting into short labeled sentences.

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 complex nested-input tool with no output schema, the description covers the report's contents, all four verdict values, the contract and human page URLs. Remaining gaps are minor: the exact report structure, behavior with duplicate ids, and whether entry ordering matters are unstated.

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

Parameters4/5

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

With 67% schema coverage and a nested rule/entries structure, the description compensates well: it enumerates every entry field (id, subject, value, scope, as_of, validity period, source, priority, retired), lists all five resolution rules including the source_rank variant, and clarifies edge semantics such as value equality ignoring case/spacing/punctuation and 'no scope applies everywhere'. It repeats some schema descriptions rather than adding syntax or format examples for dates and ranks.

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 concrete verb+resource: submit knowledge entries plus a contradiction-resolution rule, and receive a signed report pairing conflicting entries. It also explicitly separates itself from wever_memory-conflict-check (agent memory vs new fact) and wever_terms-change-check (two versions of one policy), so an agent can pick the right sibling 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?

Names two sibling tools and the exact scenario each covers, which gives clear routing guidance for the closest alternatives. It does not spell out explicit when-not-use conditions or prerequisites (e.g., minimum entry count, what to do with a single-subject corpus), leaving some inference to the agent.

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