Skip to main content
Glama

Plures

Ask verified humans

ask_humans

Send a decision to ID verified people before you act on it. Several people answer independently, each confirmed with Face ID, and you get back the consensus answer and how strongly they agreed. Use it for judgment calls where being wrong is costly: evals of AI output, tone and intent, whether two things match, moderation edge cases. Send refunds, payments and other money calls with route team. Write the question so a stranger can answer it from the context alone, and never include secrets or more personal data than the decision needs. Live keys use prepaid credit at $0.20 per answer (clips cost more by length), or $0.05 per internal vote with route team; test keys are free and simulated.

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": {
      "question": "<question>",
      "options": "<options>"
    },
    "name": "ask_humans"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoWhich of the developer's apps this is for, like "support-agent". Default: PLURES_APP, then the default app
fastNoPaid speed for a decision that can't wait: served first to verified people and pushed at once, with a bonus for answers within a minute. $0.10 more per answer live. Not with route team
teamNoThe name of one of the developer's teams, like "Finance", to decide instead of the main team
routeNoverifiers (default) asks ID verified people first. team sends it straight to the developer's own people, for money and account decisions and confidential or policy calls; $0.05 per internal vote live
contextNoThe material to judge, as plain text: the AI answer and the policy it should follow, the message, the listing
optionsYes2 to 8 possible answers, e.g. ["Yes", "No"]
categoryNoA label the developer's routing rules match on, like "refunds"; the rule may choose the route and team
questionYesWhat people should decide, e.g. "Is this customer upset?"
audio_urlNoAn https recording people listen to in full before answering, such as a call your voice agent handled. Up to 3 minutes; needs media_seconds
image_urlNoAn https image shown with the question
sensitiveNoSet true for violent, graphic or disturbing content, so only people who opted in see it, behind a warning
verifiersNoHow many people answer. Default 3; use 5 for higher stakes
video_urlNoAn https video (MP4) people watch in full before answering. Up to 3 minutes; needs media_seconds. Not with audio_url
team_votesNoWith route team: how many people on the team vote; the majority decides
instructionsNoShort guidance shown under the question
wait_secondsNoHow long to wait for the answer before returning a task_id to check later. Default 45, up to 240
media_secondsNoLength of the audio or video in seconds. Required with a clip
use_precedentNoLook in the developer's judgment graph first. When people already settled cases like this (three or more close matches with the same options, all decided the same way), it's decided by precedent at once for $0.05 live; one in ten still goes to people as an audit. Not with route team

Output Schema

NameRequiredDescriptionDefault
kindNo
meanNo
modeYes
labelYes
routeYes
votesYes
answerYes
statusYes
answersYes
reasonsNo
signoffNo
task_idYes
agreementYes
contestedNo
with_teamYes
decided_byYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: multiple independent Face ID verified answers plus a consensus strength score, a 45s default wait that returns a task_id, live pricing at $0.20/answer and $0.05/team vote, free test keys, and precedent caching where 1 in 10 still goes to humans. These are exactly the cost, latency and side-effect facts an agent needs before invoking a paid, non-idempotent call.

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 core action and return value, then purpose, then pricing. Dense but nearly every sentence carries operational information; the lengthy pricing parenthetical is the only portion that could be trimmed for readers who already saw the schema.

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?

For an 18-parameter, paid, open-world tool with an output schema and annotations, the description covers what is missing from structured fields: consensus semantics, latency/timeout behavior, cost model, precedent caching, and safe usage of the question. Nothing critical to invoking it correctly is absent.

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, but the description adds real meaning on top: wait_seconds returning a task_id, route team for money/confidential calls and its per-vote price, and use_precedent's precedent-plus-audit semantics. It also cautions on how to write the question and avoid secrets, which the schema does not say.

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?

"Send a decision to ID verified people before you act on it" states a concrete verb (send a decision) and resource (ID verified human panel), plus the consensus return value. It does not name or differentiate itself from the sibling ask_judgment, which is the most plausible overlapping tool, so it stops short of a 5.

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 concrete when-to-use triggers: judgment calls where being wrong is costly, evals of AI output, tone and intent, matching, moderation edge cases. It also routes money/payment decisions to the team path. There is no explicit when-not-to-use or named alternative tool, so it is strong context without exclusions.

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.