Skip to main content
Glama

Decision-trap sweep — Atom

Decision-trap sweep

decision_trap_sweep
Read-onlyIdempotent

Submit a declared decision record; get a deterministic TRAP_CLEAR / TRAPS_PRESENT / INSUFFICIENT_EVIDENCE sweep across seven trap sections (framing and classification, options, criteria before evaluation, evaluation and uncertainty, pre-mortem, rush and mood trap, decision log and review) with per-check evidence.

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": "decision_trap_sweep"
  }
}

Input Schema

NameRequiredDescriptionDefault
logNoDecision-log evidence (choice, rationale, assumptions, review date, communicated with why).
rushNoRush/mood evidence for irreversible decisions: {made_in_rush, made_in_a_mood} — both must be false.
framingNoFraming/classification evidence (decision stated, decide-by, constraints, out-of-scope, classification reversible|irreversible, stakes).
optionsNoOptions evidence: {list: [...], includes_status_quo, includes_smaller_reversible_step}.
criteriaNoCriteria evidence (listed, defined and weighted before scoring).
decisionNoDecision being swept.
premortemNoPre-mortem evidence (materiality declared, conducted, top risks hedged).
evaluationNoEvaluation evidence (method named, uncertainty flagged, probabilities estimable, expected value used).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: deterministic statuses, seven named trap sections, and per-check evidence. It stops short of explaining evidence thresholds or exactly when INSUFFICIENT_EVIDENCE is returned.

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?

The description is a single front-loaded sentence: action first, result second, coverage list third. The seven-section list is dense but necessary to convey scope, and there is no redundant wording.

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?

Given eight optional nested object parameters and no output schema, the description does well by naming the possible result statuses, the seven sections, and the presence of per-check evidence. It leaves some gaps around how missing evidence is handled and the exact response structure, but the schema and annotations cover the rest adequately.

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 100%, so the schema already explains each nested object parameter in detail. The description enumerates the seven trap areas, which helps confirm scope, but largely restates the parameter grouping rather than adding format, requiredness, or interaction details beyond the schema.

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 description states a specific action ('Submit a declared decision record') and a specific result ('deterministic TRAP_CLEAR / TRAPS_PRESENT / INSUFFICIENT_EVIDENCE sweep'). It also names the seven trap sections covered, so an agent can tell exactly what this tool evaluates rather than guessing from the name alone.

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 imperative 'Submit a declared decision record' gives a clear trigger for when to use the tool, and the result description clarifies its purpose. It does not state when not to use it or name alternatives, but there are no sibling tools supplied and the usage context is otherwise clear.

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.