Skip to main content
Glama

Scan for multi-attester disagreement

emem_memory_contradictions
Read-onlyIdempotent

Detect where independent sources disagree on the same cell, band, and time; return each conflict with a severity score and citations so you know when not to trust a single answer.

Instructions

Find where the corpus DISAGREES with itself (algebra: competing evidence). Two or more independent sources can sign different values for the same place, band and time. This tool returns that disagreement with a severity from 0 to 1 and a citation for each disputed fact. It does not pick one value and hide the conflict. It tells you when not to trust a single answer. Read the SCOPE before you quote a zero. By default it counts two kinds: two DIFFERENT attesters that disagree, and one responder that answers from two upstreams. disagreement_scope names the kind.

When to use: Call this before you rely on a number: 'do the sources agree on X', 'audit this claim'. Use cell_prefix for a region and band for one band family. min_severity removes small differences. Severity depends on the band kind: for a scalar, the spread over the band's range. For a vector, 1 minus the mean cosine. For a category, 1 minus the share of the mode. On a single-responder node, add include_same_attester_sources: true. There, the most likely disagreement is one signer that answers from two providers. Each record names its disagreement_scope. The receipt cites every disputed cid. To measure a pair, use emem_diff. To read the disagrees_with edge, use emem_edges_recall.

Example arguments: {"cell_prefix":"damO","band":"indices.ndvi","min_severity":0.2}

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": "emem_memory_contradictions"
  }
}

Input Schema

NameRequiredDescriptionDefault
bandNoBand key filter (e.g. `indices.ndvi`). Omit to include all bands.
cellNoAlias for `cell_prefix`, and the spelling the rest of the surface uses for a cell64. Send a cell64 you already hold and the scan narrows to that place instead of running over the corpus.
limitNoMax contradictions to return.
cell64NoAlias for `cell_prefix`.
cell_prefixNoA cell64 to scan, or a bytewise prefix of one (e.g. `defi.zb5f9`). Omit to scan the whole corpus up to the scan cap. A full cell64 is a prefix of itself, so passing one narrows the scan to exactly that place.
min_severityNoSeverity floor in [0, 1]. 0 = report every disagreement, 1 = only flagrant. Severity scoring is per band kind: scalar (max-min over band range), vector (1 - mean cosine), categorical (1 - mode share).
resume_afterNoThe `resume_after` of a scan that stopped at its time budget. The scan continues from the next key.
window_unix_sNo[lo, hi] inclusive Unix-seconds filter on attestations' signed_at, all disagreeing attestations must fall in the window.
include_same_attester_sourcesNoDefault true: also report keys where ONE attester answered from two upstreams (a changed `derivation.fn_key` or `sources[].scheme` set). A re-signed provider is a refresh and stays out. Each record names its `disagreement_scope`. Pass false for distinct attesters only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.4.5
    • changedInput schema / properties / include_same_attester_sources / default
      Previous value: -falseNew value: +true
    • changedInput schema / properties / include_same_attester_sources / description
      Previous value: -"Also report keys where ONE attester answered the same address from two different upstreams. Default false, which scans only for disagreement between two or more DISTINCT attesters — so on a single-responder corpus a zero here means the narrower question was answered, not that nothing disagrees. Set true and a key qualifies when the facts differ in `derivation.fn_key` or in their `sources[].scheme` set; the same provider re-signed is a refresh, not a disagreement, and stays excluded. Each record carries `disagreement_scope` and a `providers[]` list naming what changed."New value: +"Default true: also report keys where ONE attester answered from two upstreams (a changed `derivation.fn_key` or `sources[].scheme` set). A re-signed provider is a refresh and stays out. Each record names its `disagreement_scope`. Pass false for distinct attesters only."
    • addedInput schema / properties / resume_after
      Added value: +{
      +  "description": "The `resume_after` of a scan that stopped at its time budget. The scan continues from the next key.",
      +  "type": "string"
      +}
  2. Changed3 schema fields changedv2.4.4
    • addedInput schema / properties / cell
      Added value: +{
      +  "description": "Alias for `cell_prefix`, and the spelling the rest of the surface uses for a cell64. Send a cell64 you already hold and the scan narrows to that place instead of running over the corpus.",
      +  "type": "string"
      +}
    • addedInput schema / properties / cell64
      Added value: +{
      +  "description": "Alias for `cell_prefix`.",
      +  "type": "string"
      +}
    • changedInput schema / properties / cell_prefix / description
      Previous value: -"Bytewise prefix on cell64 (e.g. `defi.zb5f9`). Omit to scan the whole corpus up to the scan cap."New value: +"A cell64 to scan, or a bytewise prefix of one (e.g. `defi.zb5f9`). Omit to scan the whole corpus up to the scan cap. A full cell64 is a prefix of itself, so passing one narrows the scan to exactly that place."
  3. Changed1 schema field changedv1.3.10
    • addedInput schema / properties / include_same_attester_sources
      Added value: +{
      +  "default": false,
      +  "description": "Also report keys where ONE attester answered the same address from two different upstreams. Default false, which scans only for disagreement between two or more DISTINCT attesters — so on a single-responder corpus a zero here means the narrower question was answered, not that nothing disagrees. Set true and a key qualifies when the facts differ in `derivation.fn_key` or in their `sources[].scheme` set; the same provider re-signed is a refresh, not a disagreement, and stays excluded. Each record carries `disagreement_scope` and a `providers[]` list naming what changed.",
      +  "type": "boolean"
      +}
  4. Changed1 schema field changedv1.3.1
    • changedInput schema / properties / window_unix_s / description
      Previous value: -"[lo, hi] inclusive Unix-seconds filter on attestations' signed_at — all disagreeing attestations must fall in the window."New value: +"[lo, hi] inclusive Unix-seconds filter on attestations' signed_at, all disagreeing attestations must fall in the window."
  5. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description adds real behavior beyond it — the two disagreement kinds counted by default, the severity formulas per band kind, the scan cap and time budget with resume_after, and the warning that a zero result does not necessarily mean agreement. That last caveat ('read the SCOPE before you quote a zero') is exactly the kind of trap disclosure that matters, but 'SCOPE' is left undefined, so the agent cannot be sure whether it means an output field or a general caution.

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 and the 'When to use' block are correctly front-loaded, and the inline example arguments are useful. But the body is a dense run-on that re-states the severity formulas already in the schema, repeats the `disagreement_scope` point twice, and leans on capitalized shouting plus unexplained domain jargon ('algebra: competing evidence', 'responder', 'signer', 'upstreams') that slows an agent down rather than speeding it up.

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 nine optional parameters, no output schema, and annotations covering only safety, the description carries most of the burden — and it does describe the return shape at a usable level (each record names its disagreement_scope, the receipt cites every disputed cid) plus pagination via limit and resume_after. The remaining gap is that the scan cap and time budget are referenced but never quantified, so the agent cannot predict truncation.

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?

Schema coverage is 100%, so the baseline is 3, and much of the parameter prose is duplicated from the schema (severity formulas appear in both min_severity and the description). What lifts it above baseline is selection guidance the schema does not give — using cell_prefix for a region versus band for a band family, that min_severity simply removes small differences, and the directive to set include_same_attester_sources on single-responder nodes.

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 sentence states a specific verb and resource — finding where the corpus disagrees with itself — and immediately scopes what it will not do ('does not pick one value and hide the conflict'). It also names the sibling tools that serve adjacent needs (emem_diff for a pair, emem_edges_recall for the edge), so an agent can place it in the family without opening a schema.

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?

It gives an explicit trigger ('call this before you rely on a number', 'do the sources agree on X', 'audit this claim'), tells the agent which parameter selects which scenario (cell_prefix for a region, band for one band family, include_same_attester_sources on a single-responder node), and routes two adjacent tasks to named alternatives. That is when-to-use, how-to-scope, and when-to-go-elsewhere in one pass.

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