Skip to main content
Glama

Respond on behalf of a person

respond_to_decision
DestructiveIdempotent

Record one person's answer, only when that person asked you to. Which fields you need depends on the decision's type (get_decision shows it in respond.fields):

  • poll: voter_id + option (exact label) or option_id

  • ranking: voter_id + order (every option label or id, best first)

  • checkin: name + status (in, maybe, out)

  • availability: name + slot_ids (from get_decision slots) Answering again with the same voter_id or name (case-insensitive) replaces that person's earlier answer.

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": {
      "decision_id": "<decision_id>"
    },
    "name": "respond_to_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNocheckin, availability: the person's name.
orderNoranking: every option label or id, best first.
optionNopoll: exact option label.
statusNocheckin
slot_idsNoavailability: every slot the person can make.
voter_idNopoll, ranking: stable id for the person, e.g. their name.
option_idNopoll: option id (alternative to option).
decision_idYesDecision id or SettleIt link, e.g. "AbC123xYz9" or "https://settleit.now/p/AbC123xYz9".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description earns credit for explaining exactly how overwriting works — re-answering with the same voter_id or name (case-insensitive) replaces the earlier answer. The consent precondition adds an authorization constraint the annotations cannot express. It does not cover auth requirements or what a successful response looks like, so not a 5.

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?

Purpose and precondition are front-loaded in one sentence, followed by a compact per-type bullet list and a final sentence on replacement. Every line carries information the agent needs; there is no filler.

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 an 8-parameter, four-modality tool with no output schema, the description covers all conditional paths and the overwrite rule. Only the return value and error behavior are unaddressed, which is a minor gap given annotations already signal the mutation profile.

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 would be 3; the description exceeds it by mapping which parameter combinations are needed per decision type (poll vs ranking vs checkin vs availability) and by flagging "exact label" matching and best-first ordering. It also ties the fields to get_decision's `respond.fields`, which the schema alone does not.

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?

States a specific verb and resource ("Record one person's answer") plus the scope limitation that it is on someone's behalf. That distinguishes it immediately from create_decision, get_decision, and the close/reopen siblings, which operate on the decision rather than an individual's response.

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 precondition ("only when that person asked you to") and routes the agent to get_decision to discover `respond.fields` before choosing parameters. That covers both when to use it and what to do first, leaving little to inference.

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.

Resources