Skip to main content
Glama
Sign In

Ask a Human (Tech & Toast)

by io.github.pgraci
OverviewDiscussionsAdmin

Ask for a kind of human we do not have yet

request_human

Free. Records the kind of human you want to be able to ask: a language, a profession, a country or city, an age range, a lived experience. New humans are recruited from these requests.

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": {
      "api_key": "<api_key>",
      "description": "<description>"
    },
    "name": "request_human"
  }
}

Input Schema

NameRequiredDescriptionDefault
api_keyYes
languageNoLanguage the human should answer in, e.g. es, pt-BR, Jamaican Patois
specialtyNoProfession or domain, e.g. nurse, farmer, immigration lawyer, chef
descriptionYesWho you need, in plain words

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare a non-destructive, non-idempotent write; the description adds two things they don't: the request is 'Free' (no credits) and new humans are recruited from requests, implying asynchronous fulfillment rather than an immediate answer. It stops short of saying how the agent learns the outcome (e.g., check_human_status).

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?

Two short sentences, front-loaded with the cost signal ('Free.') and then the core behavior. No filler.

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?

Adequate for a simple 4-parameter write, but it omits the post-request lifecycle – whether a request is queued, how long it takes, and that check_human_status is the follow-up – which an agent needs to use this correctly in a workflow.

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 75% and each parameter already carries an example-laden description, so the schema does the heavy lifting. The description's mention of language, profession, country/city, age range, and lived experience loosely maps to language/specialty/description but adds no format or constraint detail.

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: records a request for a human profile that doesn't exist yet, with examples of the dimensions (language, profession, geography, age, lived experience). Clear against siblings like ask_human and list_humans, though the alternative is not explicitly named.

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?

'Records the kind of human you want to be able to ask' plus the title imply this is for gaps in coverage, but the description never states when to use this versus ask_human or list_humans, nor what to do if a matching human already exists. Usage is inferable but not directed.

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

All Ask a Human (Tech & Toast) toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources