Skip to main content
Glama

Answer a question

answer_question
DestructiveIdempotent

Answer a question on a Request, including still_want (yes or pause).

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": {
      "request_id": "<request_id>",
      "question_id": "<question_id>",
      "answer": "<answer>"
    },
    "name": "answer_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
answerYeschoice: one of the question’s choices (yes or pause for still_want). text: the number (money_minor: cents for USD). null: the person doesn’t know.
request_idYesThe Request’s id from list_requests.
question_idYesThe question’s id from get_request, or still_want.
request_keyNoOptional. The same key repeats a change safely; one is derived when left out.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed27 schema fields changed
    • addedInput schema / properties / answer
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "choice: one of the question’s choices (yes or pause for still_want). text: the number (money_minor: cents for USD). null: the person doesn’t know.",
      +  "properties": {
      +    "choice": {
      +      "anyOf": [
      +        {
      +          "maxLength": 80,
      +          "minLength": 1,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "text": {
      +      "anyOf": [
      +        {
      +          "maxLength": 80,
      +          "minLength": 1,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
    • removedInput schema / properties / answers
      Removed value: -{
      -  "description": "One {key, value} per question item; null if the user did not know.",
      -  "items": {
      -    "additionalProperties": false,
      -    "properties": {
      -      "key": {
      -        "pattern": "^[a-z][a-z0-9_]{0,39}$",
      -        "type": "string"
      -      },
      -      "value": {
      -        "anyOf": [
      -          {
      -            "type": "boolean"
      -          },
      -          {
      -            "type": "number"
      -          },
      -          {
      -            "maxLength": 80,
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      }
      -    },
      -    "required": [
      -      "key",
      -      "value"
      -    ],
      -    "type": "object"
      -  },
      -  "maxItems": 5,
      -  "minItems": 1,
      -  "type": "array"
      -}
    • removedInput schema / properties / intent_id
      Removed value: -{
      -  "description": "The Request's ID.",
      -  "format": "uuid",
      -  "type": "string"
      -}
    • removedInput schema / properties / provenance
      Removed value: -{
      -  "description": "human_stated: the user said this. agent_inferred: you concluded it from context without asking. Never present an inference as the user’s statement.",
      -  "enum": [
      -    "human_stated",
      -    "agent_inferred"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / properties / question_id / anyOf
      Added value: +[
      +  {
      +    "const": "still_want",
      +    "type": "string"
      +  },
      +  {
      +    "pattern": "^[0-9a-f-]{36}(:[a-z][a-z0-9_]{0,39})?$",
      +    "type": "string"
      +  }
      +]
    • changedInput schema / properties / question_id / description
      Previous value: -"The question's ID."New value: +"The question’s id from get_request, or still_want."
    • removedInput schema / properties / question_id / format
      Removed value: -"uuid"
    • removedInput schema / properties / question_id / type
      Removed value: -"string"
    • addedInput schema / properties / request_id
      Added value: +{
      +  "description": "The Request’s id from list_requests.",
      +  "format": "uuid",
      +  "type": "string"
      +}
    • changedInput schema / properties / request_key / description
      Previous value: -"Your key for this change; the same key repeats it safely."New value: +"Optional. The same key repeats a change safely; one is derived when left out."
    • changedInput schema / required
      Previous value: -[
      -  "intent_id",
      -  "question_id",
      -  "answers",
      -  "provenance",
      -  "request_key"
      -]New value: +[
      +  "request_id",
      +  "question_id",
      +  "answer"
      +]
    • changedOutput schema / properties / result / additionalProperties
      Previous value: -falseNew value: +{}
    • removedOutput schema / properties / result / properties / answer_id
      Removed value: -{
      -  "format": "uuid",
      -  "type": "string"
      -}
    • removedOutput schema / properties / result / properties / counted
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / result / properties / effect / enum
      Removed value: -[
      -  "counted",
      -  "pending",
      -  "note",
      -  "retracted"
      -]
    • changedOutput schema / properties / result / properties / effect / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / result / properties / execution_available
      Removed value: -{
      -  "const": false,
      -  "type": "boolean"
      -}
    • addedOutput schema / properties / result / properties / next_step
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • removedOutput schema / properties / result / properties / provenance
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "description": "human_stated: the user said this. agent_inferred: you concluded it from context without asking. Never present an inference as the user’s statement.",
      -      "enum": [
      -        "human_stated",
      -        "agent_inferred"
      -      ],
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ]
      -}
    • removedOutput schema / properties / result / properties / question_id / format
      Removed value: -"uuid"
    • removedOutput schema / properties / result / properties / question_status
      Removed value: -{
      -  "enum": [
      -    "open",
      -    "answered",
      -    "needs_interpretation",
      -    "expired",
      -    "cancelled",
      -    "superseded"
      -  ],
      -  "type": "string"
      -}
    • addedOutput schema / properties / result / properties / recorded
      Added value: +{
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / result / properties / recorded_at
      Removed value: -{
      -  "format": "date-time",
      -  "type": "string"
      -}
    • removedOutput schema / properties / result / properties / request_id / format
      Removed value: -"uuid"
    • removedOutput schema / properties / result / properties / requires_scope
      Removed value: -{
      -  "const": "purchases:agent_judgement",
      -  "type": "string"
      -}
    • removedOutput schema / properties / result / properties / status
      Removed value: -{
      -  "enum": [
      -    "accepted",
      -    "needs_interpretation"
      -  ],
      -  "type": "string"
      -}
    • changedOutput schema / properties / result / required
      Previous value: -[
      -  "question_id",
      -  "request_id",
      -  "answer_id",
      -  "status",
      -  "counted",
      -  "effect",
      -  "provenance",
      -  "question_status",
      -  "recorded_at",
      -  "execution_available"
      -]New value: +[
      +  "request_id",
      +  "question_id",
      +  "recorded",
      +  "effect",
      +  "next_step"
      +]
  2. First observed

TDQS

C2.9/5.0
Behavior2/5

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

Annotations declare destructiveHint=true and idempotentHint=true, but the description never explains what is permanent about submitting an answer, whether it can be changed afterwards, or how the optional request_key makes a repeat call safe. The only added context is the still_want special case (yes or pause).

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?

A single short sentence, front-loaded with the action, with no filler. It is efficient, though it is perhaps too terse given the destructive nature of the operation.

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?

An output schema and a fully described input schema carry much of the burden, so the description needn't explain return values. However, for a destructive, non-readOnly mutation with a nested answer object, the description omits the consequences of answering and the idempotency behavior, leaving meaningful gaps.

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 the meaning of request_id, question_id, answer (text vs choice) and request_key is already documented in the schema. The description restates the still_want choice but adds no syntax or format detail beyond it, so the baseline 3 applies.

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 ('Answer a question on a Request') and identifies the special still_want question type. It does not differentiate itself from siblings such as update_request or respond_to_offer, so an agent can't fully rule out alternatives from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Use is only implied by the phrase 'Answer a question on a Request'. There is no statement of when to choose this over update_request, respond_to_offer, or close_request, and no prerequisites or exclusions are given.

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