Skip to main content
Glama

Explain a past decision (why the agent acted)

explain_decision
Read-only

Reconstruct why an agent acted from its recorded action and exact beliefs at that moment, even if later superseded, and verify the decision's signed receipt.

Instructions

Reconstruct why an agent acted: the recorded action and the exact beliefs it held at that moment — even if those facts have since been superseded, retracted, or erased. Also verifies the decision's signed receipt so you know the record itself wasn't altered.

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": {
      "decision_id": "<decision_id>"
    },
    "name": "explain_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
user_idNodefault
decision_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

B3.4/5.0
Behavior4/5

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

Annotations establish readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. Beyond that, the description adds substantive behavior: the result reflects the historical belief state even when facts were later superseded or erased, and the call also verifies a signed receipt for tamper detection. It does not say what happens when verification fails (error vs. flag), but the output schema covers returns.

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

Conciseness4/5

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

Two dense sentences, front-loaded with the core purpose and followed by the two differentiating traits (historical state, receipt verification). No filler, though the em-dash aside is slightly heavy for the amount of information conveyed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With annotations and an output schema present, the return shape and safety profile are handled elsewhere, and the description covers the conceptual result well. The remaining gap is the unexplained user_id default and the decision_id format, plus no note on what a failed receipt verification yields — notable for a tool whose output the agent is meant to trust.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry parameter meaning, and it does not mention decision_id at all or explain the user_id scoping parameter with its "default" value. An agent gets no guidance on the identifier format or on how user_id affects which record is resolved.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Reconstruct why an agent acted: the recorded action and the exact beliefs it held at that moment" states a specific verb and resource, and the 'even if superseded/retracted/erased' clause defines the scope of what is returned. It is clearly not a write or listing operation, distinguishing it conceptually from record_decision and audit_log, though no sibling is named directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied by the framing — you call this to explain a past decision after the fact — but there is no explicit when-to-use vs. when-not guidance and no named alternative (e.g., history or audit_log) to route the agent. The description also omits any prerequisite about needing a decision_id from a prior action.

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