Skip to main content
Glama

edit_deploy

Update Deploy tab settings via theme, structure, distribution, github_sync, field_mode, recruitment, my_notifications, or power_analysis patches. power_analysis partially updates the saved, reproducible analysis plan and reads the merged plan back; inspect question and Flow structure before selecting comparison cells or a conjoint question. my_notifications sets your own push/email notifications for this survey (first response, every-N completes, quality flags, quota nearly full/reached). recruitment.connect is a one-click panel setup: study link macros, completion/screen-out/over-quota/quality redirects on end screens, and quota rerouting. Anything that pays participants (approving, bonuses, launching or resizing a paid study) is app-only. 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

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": {
      "survey_id": "<survey_id>"
    },
    "name": "edit_deploy"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNoTheme, branding, logos, or workspace preset patches
structureNoRunner structure, survey options, or collection policy
survey_idYesSurvey UUID
field_modeNoField/offline-administration link: an interviewer opens it once online, then can administer the survey to many respondents while fully offline; each response queues on the device and syncs automatically once back online.
github_syncNoGitHub Sync repository creation
recruitmentNoOne-click recruitment-provider setup (Prolific, CloudResearch Connect/Prime Panels, Cint, SONA, YouGov, Rep Data, other panels): connect, reapply, disconnect, or route screen-out/quality answers to their end screens. Acting on a live study at Prolific or Connect is manage_recruitment; paying participants stays in the app. Read the result back with read_deploy include ["recruitment"].
distributionNoPersonalized link batches and recipients
power_analysisNoSaved Deploy → Power assumptions. Partial patches merge into the existing versioned analysis plan; read back with read_deploy include ["power_analysis"].
my_notificationsNoThe signed-in person's own notifications for this survey — the Deploy tab's My Notifications card. Per event: mode (default/on/off), push, email, and its threshold (every, min_severity, percent). Set mode default on every event to clear the overrides. Collaborators use mode on to follow a survey they don't own. These notify the person in the app, by push, and by email; for webhooks to an agent, subscribe to the matching MCP event instead. Returns the same shape as read_deploy include ["my_notifications"].

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, it discloses key behaviors: power_analysis partially merges into a saved plan and reads it back, recruitment.connect is safe to call again, reapply fixes deleted end screens and hand-edited redirects, and disconnect leaves end screens in place. It also explains app-only boundaries and that paying participants stays in the app.

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?

The purpose and patch list are front-loaded, and the density is justified by the tool's complexity. The paragraph is long and occasionally run-on, but most sentences carry operational constraints or alternatives that an agent needs.

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?

For a nine-parameter nested mutation tool with an output schema, the description covers merge semantics, read-back paths, app-only exclusions, sibling alternatives, and provider-specific setup behavior. Nothing essential for correct invocation appears to be missing.

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?

The schema already has 100% description coverage, so the baseline is high. The description adds patch-level semantics that the schema cannot convey, especially that power_analysis merges partial updates and that recruitment.connect reuses or creates end screens, but it does not separately explain every top-level patch parameter.

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: 'Update Deploy tab settings via theme, structure, distribution, github_sync, field_mode, recruitment, my_notifications, or power_analysis patches.' It enumerates the patch areas and explicitly distinguishes the tool from read_deploy by describing read-back patterns and app-only exclusions.

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?

It provides explicit when-to-use guidance for each patch area, such as inspecting question and Flow structure before selecting comparison cells or a conjoint question, and explains when to use recruitment.connect versus manage_recruitment for live studies. It also names app-only alternatives for participant payments, preregistration links, and instrument locking.

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