Skip to main content
Glama

Refute a record

padam_refute
Destructive

Marks a retrieved record as no longer true and lowers confidence without refreshing it; repeated refutations archive it from search while keeping history.

Instructions

Mark a retrieved record as no longer true. Lowers confidence without refreshing the record. After enough refutations the record leaves search and is archived, but stays in history. Identity and preference records are never archived through this tool: only the owner can do that from the console.

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": {
      "id": "<id>"
    },
    "name": "padam_refute"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesRecord id, as returned by padam_search or padam_write
dropNoHow much confidence to remove, at most 0.5 per call

Output Schema

NameRequiredDescriptionDefault
idYes
refutedYes
protectedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.2
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "id": {
      +      "type": "string"
      +    },
      +    "protected": {
      +      "type": "boolean"
      +    },
      +    "refuted": {
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "id",
      +    "refuted",
      +    "protected"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.4.8

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only flag destructiveHint=true; the description goes further by explaining the mechanism (confidence drop, no refresh), the cumulative outcome (record leaves search and is archived after enough refutations), and the persistence guarantee (stays in history). It also discloses a hard scope boundary — identity and preference records are immune here — which an agent could otherwise get wrong and misreport as success.

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?

Three short sentences, each carrying distinct information: the action, the mechanism/outcome, and the scope restriction. Front-loaded with the core effect and no repetition of the schema or annotations.

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?

Return values are covered by the output schema, so the description's job is behavioral and scoping context — which it fully supplies for a destructive, cumulative mutation. Nothing an agent needs before invoking it is missing.

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% and both parameters are self-documenting, including the drop amount and its 0.5 cap, so the baseline would be 3. The description adds a small amount of meaning by framing the call as lowering confidence rather than deleting, reinforcing what the numeric effect means, but it never mentions the per-call cap or default itself.

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?

"Mark a retrieved record as no longer true" gives a specific verb (refute) and resource (record), and the follow-on sentences make clear this is the inverse of confirming — it lowers confidence and eventually archives. An agent can distinguish it from padam_confirm or padam_write 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 Guidelines4/5

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

The description establishes a clear use context (a retrieved record that is no longer true) and a scope exclusion (identity and preference records are never archived through this tool, only by the owner in the console). It stops short of explicitly naming an alternative tool or stating when-not-to-refute in favor of confirming, so guidance is clear but not fully routed.

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