Skip to main content
Glama

Invoke Human Tool

Wait for the answer

wait_for_handoff
Read-onlyIdempotent

Wait up to 50 seconds for one handoff on this account to be submitted. Returns the completed result, or status pending. Pending is success. Call it again to keep waiting. This does not change the handoff. Use it when the client does not declare the MCP Tasks extension. With Tasks, pass mode sync on send instead.

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": {
      "id": "<id>"
    },
    "name": "wait_for_handoff"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesHandoff id, hnd_...
timeout_msNoHow long to wait, from 0 to 50000. Default 20000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / timeout_ms / description
      Previous value: -"How long to wait, from 0 to 25000. Default 20000."New value: +"How long to wait, from 0 to 50000. Default 20000."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: the ~50s blocking ceiling, that 'pending' is a success outcome rather than a failure, and that repeated calls are the intended wait loop. It also explicitly states the call does not mutate the handoff.

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?

Six short sentences, front-loaded with the core behavior and return contract, followed by the retry pattern and the alternative-routing note. Every sentence carries distinct information.

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?

With only two parameters and no output schema, the description covers everything an agent needs: the blocking duration, the two possible outcomes, how to continue waiting, and when a different mechanism (Tasks/sync mode) is preferred.

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 100%, so both id and timeout_ms are already documented with format and range. The description only restates the 50-second cap already present in the schema's 0–50000 bound and adds no new semantics for the parameters.

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?

States a specific verb and resource with scope: 'Wait up to 50 seconds for one handoff on this account to be submitted', and clarifies what is returned (result or pending). It does not explicitly distinguish itself from the closest siblings get_handoff_status and get_handoff_result, which an agent could easily confuse with a single blocking poll.

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?

Gives an explicit when-to-use condition ('when the client does not declare the MCP Tasks extension') plus the alternative path ('With Tasks, pass mode sync on send instead'). It also states the usage pattern for continued waiting ('Call it again to keep waiting').

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.