Skip to main content
Glama

Plures

Ask people for their judgment

ask_judgment

Ask a panel of ID verified people for their honest view when there's no right answer to check: which of two replies, designs, headlines or model answers is better, whether a customer would accept a reply or decision, how well something meets a brief (1 to 5), or whether a design, video or generated image has a flaw. You get the spread of views, a contested flag when people genuinely split, and a sample of one line reasons. format signoff (coming soon; test keys now) asks one top rated verified person to approve or reject an action after a fresh Face ID or Touch ID check, with a written reason: use it before an action someone must be accountable for. Live keys use prepaid credit at $0.20 per answer (a panel of 5 is $1.00) or $1.00 per sign off; 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>"
    },
    "name": "ask_judgment"
  }
}

Input Schema

NameRequiredDescriptionDefault
aNocompare: version A as text
bNocompare: version B as text
appNoWhich of the developer's apps this is for. Default: PLURES_APP, then the default app
formatNoaccept (default): yes, yes with changes, no. compare: A or B (send a and b). rate: 1 to 5. flaws: looks right or has a flaw. signoff: one Trusted person approves or rejects. custom: send options
rubricNoWhat good looks like, in the developer's words, e.g. "Warm and clear, never pushy"
contextNoWhat people judge, or the shared setup for a comparison
optionsNocustom only: 2 to 8 answers
reasonsNoWhether people add a one line reason. Default sample (about one in four); sign offs always do
questionYesThe question, e.g. "Which reply would you rather receive?"
a_secondsNoLength of a_clip_url in seconds
b_secondsNoLength of b_clip_url in seconds
clip_kindNoWhether a_clip_url and b_clip_url are video (default) or audio
image_urlNoAn https image to judge, like a design or a generated image
verifiersNoPanel size. Default 5. A sign off is always 1
a_clip_urlNocompare: version A as an https video (MP4) or recording, played through before answering. Needs a_seconds
b_clip_urlNocompare: version B as an https video (MP4) or recording. Needs b_seconds
a_image_urlNocompare: version A as an https image
b_image_urlNocompare: version B as an https image
wait_secondsNoHow long to wait before returning a task_id to check later. Default 45, up to 240

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?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), it discloses things an agent could not otherwise know: prepaid credit pricing at $0.20 per answer with a $1.00 panel of 5, $1.00 per signoff, free simulated test keys, that signoff requires a fresh Face ID/Touch ID check, and that signoff is marked 'coming soon'. It also characterizes the response shape (spread of views, contested flag, sampled one-line reasons) and the wait/task_id async behavior.

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?

Purpose is front-loaded in the first clause and each subsequent sentence carries distinct information (task shapes, signoff semantics, pricing). It is a single dense run-on paragraph, though, and the pricing/signoff material could be broken out for faster scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 19-parameter, multi-format tool with an output schema, the description covers what matters: the format menu, cost model, accountability prerequisite for signoff, and the wait/task_id latency tradeoff. Minor gaps remain around how wait_seconds interacts with retrieval later and what the free test-key simulation does not cover, but nothing essential to correct invocation 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%, so all 19 parameters are already documented, which sets the baseline at 3. The description adds modest meaning by explaining the formats in prose and by tying panel size to cost ('a panel of 5 is $1.00'), but it does not clarify the roles of rubric, context, app, or the clip/image pairing rules beyond what the schema states.

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 opens with a specific verb and resource ('Ask a panel of ID verified people for their honest view') and immediately scopes it to subjective judgments with no ground truth. It then enumerates the concrete task shapes (which of two replies, would a customer accept, rate 1-5, does it have a flaw, signoff), which lets an agent distinguish it from a generic human-task tool like ask_humans without opening either schema.

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?

It gives a clear selection condition: use this 'when there's no right answer to check', and for signoff 'before an action someone must be accountable for'. That is real when-to-use guidance. It stops short of an explicit exclusion (e.g. when to use ask_humans or add_check instead), so it is not a full when/when-not statement.

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.