Skip to main content
Glama

read_deploy

Read-onlyIdempotent

Read Deploy tab settings: theme, runner structure, personalized links, GitHub Sync status, field mode, recruitment-provider integration (Prolific, CloudResearch, Cint, SONA, YouGov, Rep Data), the saved power-analysis plan, your own notifications for the survey (milestones, quality flags, quota alerts), or workspace theme presets. power_analysis returns the versioned Deploy → Power assumptions, including estimator family, alpha/power/effect, attrition, clustering, multiplicity, Flow comparison cells, simulation seed, and costs. The app's Compiled Design panel is a live, unsaved audit rather than a second configuration object: combine power_analysis with read_question and read_flow to reproduce its checks for outcome scale and requiredness, Flow reach and randomized subsets, assignment, repeated tasks or loops, quotas, quality rules, and linked panel data. Preregistration links and instrument locking are app-only because OSF drafts may require a saved credential and locking uses the app's canonical instrument fingerprint; use Deploy → Preregistration in Domandata.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_deploy"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax distribution recipients per batch (default: 100)
tokenNoWhen set, resolves one personalized recipient URL (with that recipient's contact; refused on a connection restricted from participant data in Settings → Integrations)
confirmNoRequired (true) for participant-level data: includes prolific_submissions, prolific_messages, cloudresearch_assignments, cloudresearch_messages, and distribution with batch_id. Confirm with the researcher before reading identifiable participant data.
includeNoDefaults to theme, structure, distribution, github_sync, field_mode, recruitment, my_notifications, and power_analysis when survey_id is set. my_notifications is the signed-in person's own fieldwork notifications for this survey (first response, milestones, quality flags, quota nearly full, quota reached): each event's override, the account-wide defaults it falls back to, and an effective plain-language summary. recruitment returns the connected provider's study link (with the provider's macros), what to set in the provider's dashboard, each outcome's end screen and redirect, a test link, and setup issues — or, when nothing is connected, every provider and its settings. recruitment_activity (not in the defaults) is the linked Prolific study's or Connect project's activity log, newest first (latest 50): each entry's time, kind (approved, rejected, bonus_paid, launched, published, paused, places_added, auto_approved, auto_paused, unscheduled, messaged, blocked, error, …), a plain-language summary, count, amount and currency, and who did it (actor "automatic" for Domandata's background job). Use it to tell the researcher what was paid and what happened automatically. prolific_submissions (not in the defaults: it calls Prolific) lists the linked Prolific study's submissions matched to responses — status, times, timeTakenSeconds, the completion code entered (studyCode), paymentStatus, and when a return was requested (returnRequestedAt) — each with an approve/review recommendation (approving pays participants, so it happens in the app). cloudresearch_project, cloudresearch_assignments, and cloudresearch_targeting (not in the defaults: they call CloudResearch Connect) return the linked Connect project's status, size, cost, progress, account balance, and settings (days_to_auto_approve, max_minutes, instructions, system_requirements, sensitive_content, languages; Connect's auto-pay window is read-only here because it pays participants, so set it in the app); its assignments matched to responses (response_id), each with Pending/Approved/Rejected status, start and finish times, pay, bonus paid, completion code, how they finished (finished_through: CompletionCode, or Redirect, which carries no code), every Connect profile answer the participant shared (connect_profile), and an approve/review recommendation; and what a new project can target: demographic criteria, the account's past projects (same_survey marks this survey's), participant groups, quota_suggestions mirroring the survey's quotas, and suggested_settings (requirements from the survey's questions, its languages Connect supports, a 3× time limit). cloudresearch_messages lists participants of the linked project with unread replies, or — with participant_id — that participant's conversations and messages (reply with edit_deploy recruitment.cloudresearch_message). prolific_study, prolific_targeting, and prolific_messages (not in the defaults: they call Prolific) are the same for Prolific: the linked study's status, places, progress counts, cost, and balance, whether Prolific's events reach Domandata live (live_updates; otherwise it checks every 15 minutes), and when Prolific last reported a high return rate (high_return_rate_at); what a new study can target (screeners, past studies with same_survey, participant groups, quota_suggestions, the pay floor, pay_history: the account's median pay per hour as estimated and as approved participants really took, in minor units, and block_list: the "Domandata block list" group every new study leaves out, with its size); and unread replies or one participant's conversations.
team_idNoWorkspace UUID for workspace_presets (default: personal workspace)
batch_idNoWith include distribution: list this batch's recipients (participant contact data, so confirm is required, and a connection restricted from participant data in Settings → Integrations is refused).
survey_idNoSurvey UUID (required for survey-scoped sections)
participant_idNoWith include cloudresearch_messages or prolific_messages: read this participant's conversations.

Output Schema

NameRequiredDescriptionDefault
resultYes

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?

The annotations already establish readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. The description adds substantial behavioral context beyond those annotations: participant-level data requires confirm, restricted connections are refused, some includes call Prolific or CloudResearch, live updates may arrive every 15 minutes, and payment-related actions are app-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the description is extremely long and dense, with many run-on sentences and repeated schema details. The complexity of the tool justifies some length, but the duplication and density reduce conciseness.

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?

Given the tool's complexity, the description is complete: it covers the available sections, defaults, confirmation requirements, external-provider behavior, app-only limitations, and how to combine power_analysis with read_question and read_flow. An output schema exists, so return-value details need not be explained further.

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 schema already documents all eight parameters, including the large include enum. The description repeats much of that parameter detail rather than adding new meaning beyond the schema, so the baseline score of 3 is appropriate.

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: "Read Deploy tab settings," then enumerates the settings covered, including theme, structure, recruitment, notifications, and power analysis. It also distinguishes this tool from read_question and read_flow by explaining how to reproduce the Compiled Design panel and notes that preregistration and locking are app-only.

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 clear usage context: defaults for include, which sections require confirm, which calls hit external providers, and which actions must happen in the app rather than through this tool. It also points to edit_deploy for replying to CloudResearch messages. It stops short of an explicit when-to-use-this-vs-edit_deploy statement, so it is strong but not fully exhaustive.

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