Skip to main content
Glama

ScoreStory

by eu.scorestory
OverviewDiscussionsAdmin

Create survey

create_survey

Create a new survey. Nothing is sent to anyone yet: afterwards, share it with create_shared_link or invite_participant.

Input Schema

NameRequiredDescriptionDefault
goalNoOne or two sentences on what the organisation wants to learn. The interviewer reads it to steer its questions.
nameYesName of the survey, e.g. "Helpdesk Q4". 1 to 255 characters.
themesNoSubjects the interviewer should explore, e.g. ["Communication", "Workload"]. Three to five is typical; add more later with add_theme.
scale_maxNoHighest point of the scale, greater than scale_min. Required when metric_type is scale.
scale_minNoLowest point of the scale. Required when metric_type is scale; the range scale_min..scale_max spans at most 20 points.
metric_typeYesThe score every interview opens with. One of: nps (Net Promoter Score), enps (employee NPS), csat (customer satisfaction), ces (customer effort score), scale (a custom numeric range, which needs scale_min and scale_max).
interview_localeYesLanguage the AI interviewer speaks. One of: nl, en, de, fr, es, it, pl, pt, or auto to follow each participant's browser language.
anonymous_responsesNoIf true, answers are never linked to who gave them, permanently.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / anonymous_responses / description
      Added value: +"If true, answers are never linked to who gave them, permanently."
    • addedInput schema / properties / goal / description
      Added value: +"One or two sentences on what the organisation wants to learn. The interviewer reads it to steer its questions."
    • addedInput schema / properties / interview_locale / description
      Added value: +"Language the AI interviewer speaks. One of: nl, en, de, fr, es, it, pl, pt, or auto to follow each participant's browser language."
    • addedInput schema / properties / metric_type / description
      Added value: +"The score every interview opens with. One of: nps (Net Promoter Score), enps (employee NPS), csat (customer satisfaction), ces (customer effort score), scale (a custom numeric range, which needs scale_min and scale_max)."
    • addedInput schema / properties / name / description
      Added value: +"Name of the survey, e.g. \"Helpdesk Q4\". 1 to 255 characters."
    • addedInput schema / properties / scale_max / description
      Added value: +"Highest point of the scale, greater than scale_min. Required when metric_type is scale."
    • addedInput schema / properties / scale_min / description
      Added value: +"Lowest point of the scale. Required when metric_type is scale; the range scale_min..scale_max spans at most 20 points."
    • addedInput schema / properties / themes / description
      Added value: +"Subjects the interviewer should explore, e.g. [\"Communication\", \"Workload\"]. Three to five is typical; add more later with add_theme."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is largely covered. The description adds genuine value beyond them by clarifying that creation alone has no external effect and that distribution is a separate explicit step. It does not mention whether the survey is editable or deletable afterwards.

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 action and followed by the constraint and the alternatives. Nothing is padding.

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?

With 8 parameters fully documented in the schema and no output schema, the description need not explain fields or return values. The one minor gap is that it does not mention that the created survey's identifier is what you pass to the sharing tools, but the workflow intent is complete enough to call correctly.

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%, with metrics, locales, scale constraints and anonymity all documented inline. The description adds no parameter-level meaning of its own, so the baseline 3 applies.

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 ("Create a new survey") and immediately separates it from the downstream sharing siblings by noting nothing is sent yet. An agent can distinguish this creation step from create_shared_link/invite_participant without opening a 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?

Explicitly names the follow-up tools (create_shared_link, invite_participant) and the condition under which they are needed, which gives clear sequencing guidance. It stops short of stating when a survey should be created at all, but the context is unambiguous for this workflow.

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

All ScoreStory 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