Skip to main content
Glama

emet_client_approve

Destructive

Approve or deny pending client tags, or prepare a writer request for owner review and decision in EMET.

Instructions

Approve or deny a pending client tag, or prepare a new writer. decision prepare drafts a writer request: client, claimed tag, door (member or guest), reason, and correlation_id. The hub login prepares that draft. The server validates it. Validation is a check and is not approval. The owner decides a new writer on /owner/chooser with the owner session. No AI grants a writer, including the hub login and the retired owl account. The owner login may still approve or deny a pending client tag. Pending client tags are listed in emet_initialize and emet_status as client_approvals.

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": {
      "tag": "<tag>",
      "decision": "<decision>"
    },
    "name": "emet_client_approve"
  }
}

Input Schema

NameRequiredDescriptionDefault
asNoRequired when the client_id already has approved tags: add keeps them all (several bots on one shared client); rename retires one
tagYesThe pending client's tag, as listed in client_approvals.pending. For decision prepare, this is the claimed tag when claimed_tag is omitted.
doorNoFor decision prepare: member is a writer. Guest is not a writer.
fromNoWith as=rename on a client that has several approved tags: the tag being replaced
clientNoFor decision prepare: the client id the writer request names.
reasonNoNote kept with the decision, or the reason on a prepared writer request.
decisionYes
claimed_tagNoFor decision prepare: the tag the writer would be known by.
correlation_idNoFor decision prepare: 16 lowercase hex characters. The same id again returns the retained request.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.3.2
    • addedInput schema / properties / claimed_tag
      Added value: +{
      +  "description": "For decision prepare: the tag the writer would be known by.",
      +  "type": "string"
      +}
    • addedInput schema / properties / client
      Added value: +{
      +  "description": "For decision prepare: the client id the writer request names.",
      +  "type": "string"
      +}
    • addedInput schema / properties / correlation_id
      Added value: +{
      +  "description": "For decision prepare: 16 lowercase hex characters. The same id again returns the retained request.",
      +  "type": "string"
      +}
    • changedInput schema / properties / decision / enum
      Previous value: -[
      -  "approve",
      -  "deny"
      -]New value: +[
      +  "approve",
      +  "deny",
      +  "prepare"
      +]
    • addedInput schema / properties / door
      Added value: +{
      +  "description": "For decision prepare: member is a writer. Guest is not a writer.",
      +  "enum": [
      +    "member",
      +    "guest"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / reason / description
      Previous value: -"Optional note kept with the decision"New value: +"Note kept with the decision, or the reason on a prepared writer request."
    • changedInput schema / properties / tag / description
      Previous value: -"The pending client's tag, as listed in client_approvals.pending"New value: +"The pending client's tag, as listed in client_approvals.pending. For decision prepare, this is the claimed tag when claimed_tag is omitted."
  2. Addedv0.2.5

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false; the description adds the crucial nuance that 'the server validates it' and 'validation is a check and is not approval,' preventing an agent from mistaking a prepared draft for a granted writer. It also discloses retry behavior for correlation_id ('the same id again returns the retained request'). It stops short of stating what approve/deny returns or that approval is irreversible.

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 main action is front-loaded, but the middle section circles the same point repeatedly — hub login prepares the draft, server validates, validation is not approval, no AI grants a writer including the hub login and the retired owl account. The 'retired owl account' reference is unexplained noise for a fresh agent, and the phrase 'decision prepare drafts a writer request' is grammatically awkward.

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?

For a 9-parameter, destructive, no-output-schema tool, the description covers the authority model and where pending tags live, which is the highest-risk information. However it omits the rename/add mechanics governed by as and from, and says nothing about what an approve or deny returns, so an agent still has gaps before calling correctly.

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 coverage is 89%, so parameter documentation is already largely handled by the schema. The description groups client, claimed_tag, door, reason and correlation_id under the prepare flow, which adds modest interpretive value, but it never addresses the as/from rename parameters, which carry real decision semantics. Baseline 3 for a high-coverage schema is appropriate.

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?

Opens with a specific verb+resource pair: 'Approve or deny a pending client tag, or prepare a new writer.' It also disambiguates the 'prepare' mode from approval and points to emet_initialize/emet_status as where pending tags appear, so an agent can place it among siblings without another schema read. The triple-mode framing (approve/deny/prepare) is dense but decipherable.

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?

Gives unusually explicit authority boundaries: 'The owner login may still approve or deny a pending client tag,' 'The owner decides a new writer on /owner/chooser,' and 'No AI grants a writer.' That tells the agent when this tool does NOT apply. It does not name an alternative tool for the human-only paths, but the exclusions themselves are clear.

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