Skip to main content
Glama
SmartSuiteFoundry

SmartSuite MCP Server

by SmartSuiteFoundry
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

smartsuite_create_application

Create a new SmartSuite table in a solution, optionally provisioning all its fields in one request to avoid slow follow-up additions.

Instructions

Create a new table (application) in a solution. Requires readwrite/admin mode AND SMARTSUITE_ENABLE_SCHEMA_WRITE=true. Supply a name and the solutionId. The table is created with a default "Title" primary field and a record term ("what each record is called", default "Record") — the record term is always set explicitly so it is never left empty (an empty record term can break list-view/grid widget creation against the table). PASS fields TO CREATE THE TABLE AND ALL ITS FIELDS IN ONE REQUEST: an array of { fieldType, label, params? } entries (same shape as smartsuite_create_field — params ARE honoured here, and the params that carry a field's configuration are validated: a linkedrecordfield without linked_application, or a rollup/lookup without linked_field + field_selection, is rejected rather than created half-built, and select choices get their stored value filled in from the label when omitted). This is the ONLY true bulk field path SmartSuite offers and it is dramatically faster than adding fields afterwards — one request for all of them, versus ~1s per field via smartsuite_create_fields against an existing table. So when a table is new, always create its fields here. SmartSuite also adds its own default field set (Title, Description, Assigned To, Status, Due Date, Priority, …) alongside yours. Dry-run preview unless confirm:true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesThe table name.
fieldsNoOptional: fields to provision inline with the table, in order — all in this single request. Each entry: { fieldType, label, params? }, same semantics as smartsuite_create_field. aiPrompt is not supported here (the fields it would reference do not exist yet); set AI prompts after the table exists.
confirmNoSet true to create; otherwise returns a dry-run preview.
recordTermNoWhat each record is called (singular), e.g. "request". Defaults to "record". Use lower case — SmartSuite stores the term lower-case and capitalizes it for display, so "Record" renders wrong.
solutionIdYesThe solution to create the table in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.3
    • changedInput schema / properties / recordTerm / description
      Previous value: -"What each record is called (singular), e.g. \"Request\". Defaults to \"Record\"."New value: +"What each record is called (singular), e.g. \"request\". Defaults to \"record\". Use lower case — SmartSuite stores the term lower-case and capitalizes it for display, so \"Record\" renders wrong."
  2. Changed2 schema fields changedv1.0.0
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "Optional: fields to provision inline with the table, in order — all in this single request. Each entry: { fieldType, label, params? }, same semantics as smartsuite_create_field. aiPrompt is not supported here (the fields it would reference do not exist yet); set AI prompts after the table exists.",
+  "items": {
+    "properties": {
+      "fieldType": {
+        "description": "SmartSuite field type, e.g. textfield, numberfield, singleselectfield, linkedrecordfield.",
+        "type": "string"
+      },
+      "label": {
+        "description": "Field display label.",
+        "type": "string"
+      },
+      "params": {
+        "description": "Optional sparse field params; omit to accept type defaults.",
+        "type": "object"
+      }
+    },
+    "required": [
+      "fieldType",
+      "label"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / recordTerm
      Added value: +{
+  "description": "What each record is called (singular), e.g. \"Request\". Defaults to \"Record\".",
+  "type": "string"
+}
  3. First observedv0.9.8

TDQS

A4.4/5.0
Behavior3/5

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

With only readOnlyHint=false in the annotations, the description carries the behavioral burden and does it well: it discloses the dry-run-unless-confirm:true default, the required permission mode and environment flag, the mandatory explicit record term (with the consequence that an empty one can break list-view/grid widget creation), the injected default field set, and validation rules that reject half-built linkedrecord/rollup/lookup fields. This is substantially more than the annotations provide.

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?

Dense but front-loaded: the action, prerequisites, defaults, and bulk-field guidance appear in that order. The all-caps emphasis on the fields argument is stylistically loud, but every sentence carries operational information an agent needs, with 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?

Given 5 parameters, no output schema, and near-zero annotation coverage, the description is close to complete: it covers permissions, defaults, side effects, validation, and dry-run semantics. The one omission is what the call returns and how to identify the newly created table for follow-up field/view work, which the agent would need to infer.

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 the baseline is 3, but the description adds real semantics beyond the schema: it explains that params ARE honoured (unlike some other paths), which params are validated and how invalid ones are rejected, that select choices' stored value is backfilled from the label when omitted, and that recordTerm must be lower case. The recordTerm casing detail roughly duplicates the schema, keeping this at 4 rather than 5.

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?

Opens with a specific verb+resource ('Create a new table (application) in a solution') and disambiguates SmartSuite's table/application terminology. An agent can distinguish it from smartsuite_create_solution, smartsuite_create_field, and smartsuite_create_fields from the first sentence alone.

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?

States prerequisites explicitly (readwrite/admin mode AND SMARTSUITE_ENABLE_SCHEMA_WRITE=true) and gives a strong routing rule: when a table is new, always create its fields here rather than via smartsuite_create_fields afterwards, with a speed rationale (~1s per field). It also names the sibling and the excluded case (aiPrompt must be set after the table exists).

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

Deploy Server

Other Tools