Skip to main content
Glama

Samuelz® Policy

Regeländerung aktivieren

confirm_policy
Destructive

App-only: apply the exact replacement after the Owner's trusted show_policy_approval click. Models must never invoke it. Goal/general-budget cards use confirm_business_goal instead.

The UI returns candidate+approvalToken from one card. Module/policy, replacement value, revision and expiry form one signed binding; a current revision cannot make a changed candidate or mismatched token valid. Requires current policy:read/write and Owner/module authority. Changed/expired candidates, stale revisions and revoked access fail closed.

Success returns confirmed, policyVersion and revision; consumerOutcome stays not_verified until downstream evidence exists. Read get_policy with kind=policy and the same moduleKey/policyKey for the current confirmed snapshot; get_policy_write_options supplies supported values/revisions. get_business_budgets.advertising also reads advertising pending state. On stale state renew intent; on isError/not_verified or uncertainty, read state without retrying confirmation.

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": {
      "candidate": "<candidate>",
      "approvalToken": "<approvalToken>"
    },
    "name": "confirm_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
candidateYesExact candidate from the matching card's hidden metadata, including the change and expiry. The trusted UI copies every field unchanged; never reconstruct it from chat.
approvalTokenYesOpaque approval proof supplied in hidden metadata by the matching show tool. The trusted UI copies it unchanged; never construct it or request it from chat.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and idempotentHint=false; the description adds substantial context beyond them: the signed binding of module/policy/replacement/revision/expiry, required policy:read/write and Owner/module authority, fail-closed behavior on changed or expired candidates, and the not_verified consumerOutcome. Only the return payload detail is thin, and there is no output schema, so a small gap remains.

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?

Front-loaded with the app-only restriction and the prohibited-caller warning, then proceeds to binding semantics, authority requirements, and failure/recovery guidance in order of decision importance. Dense and a bit terse in places, but no sentence is filler for a destructive confirmation tool.

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?

Covers invocation authority, trust chain, authorization requirements, fail-closed semantics, success return fields, downstream verification status, and the exact read tools (get_policy with kind=policy, get_policy_write_options, get_business_budgets.advertising) needed before or after. For a destructive, non-idempotent tool with no output schema, that is complete.

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 baseline is 3; the description nevertheless adds conceptual meaning the schema lacks, explaining that the fields form one signed binding where a current revision cannot validate a changed candidate or mismatched token. It does not re-describe value/expiresAt mechanics beyond what the schema already covers.

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 specific verb and object ('apply the exact replacement') plus a hard scope restriction ('App-only', 'Models must never invoke it'), and names a sibling alternative ('Goal/general-budget cards use confirm_business_goal instead'). The purpose and its target audience are unmistakable.

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?

Explicitly defines the precondition (Owner's trusted show_policy_approval click), the prohibition (models must never invoke it), the exception route (confirm_business_goal for budget cards), and recovery paths ('On stale state renew intent; on isError/not_verified... read state without retrying confirmation'). Alternatives and when-not conditions are both covered.

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