Skip to main content
Glama
lorkorblaq

io.github.lorkorblaq/labloop-mcp

by lorkorblaq

Escalate to a human agent

labloop_escalate_to_human

Escalate unresolved user issues to a human support agent. Use when a user requests a person, reports frustration, or faces repeated errors—logs a ticket and returns a simulated handoff.

Instructions

Hand the conversation to a human support agent (SIMULATED in this demo).

Use when the user asks for a real person, has a complaint, is frustrated, keeps hitting errors, or the request is beyond the other tools. Logs a ticket in memory and returns {status, simulated: true, ticketId, message}. No real message is sent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contextNoBrief summary of the conversation so far, so the human agent has context.
user_queryYesThe user's request or problem, in their own words.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

The annotations only set all hints to false, providing no safety or side-effect information, so the description must carry the full burden. It discloses that the action is simulated, logs a ticket in memory, returns a specific object structure, and that 'No real message is sent.' This is comprehensive and goes beyond what annotations convey.

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 three sentences: the first states the core action and simulation, the second gives usage criteria, and the third explains the outcome and return value. It is front-loaded with the primary purpose and every sentence adds value without redundancy.

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?

The tool has a clear output schema (as indicated by 'Has output schema: true'), and the description explicitly states the return structure ({status, simulated: true, ticketId, message}) and that no real message is sent. For a simple two-parameter tool with a well-defined use case and simulation caveat, nothing an agent needs to invoke it correctly is missing.

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%, with both parameters already having clear descriptions ('Brief summary of the conversation so far' and 'The user's request or problem'). The description text does not add additional semantic meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

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 clearly states the action: 'Hand the conversation to a human support agent' with a specific resource (human agent) and explicitly notes it is SIMULATED in this demo. It also differentiates from sibling tools by indicating it is for cases 'beyond the other tools' and for user frustration, giving it a distinct scope.

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?

It provides explicit conditions for use: 'when the user asks for a real person, has a complaint, is frustrated, keeps hitting errors, or the request is beyond the other tools.' This is precise and actionable, and implies that other tools should be tried first, making it clear when this tool is the appropriate fallback.

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