Skip to main content
Glama
Inistate

Inistate MCP Server

Official
by Inistate
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Submit Activity

submit_activity
Destructive

Submit one named activity to a single Inistate entry, such as create, edit, delete, or comment, with AI reasoning and confidence for auditable processing.

Instructions

Write operation: one call performs exactly one named activity on one entry of one module, and nothing else runs. The activity is the activity argument — a standard one (create [no entryId], edit, delete, changeStatus, comment, duplicate, manage) or a custom activity the workspace's designer defined (listed by get_module_schema tier=extended); activity names are data, not hidden tools. Call get_form before the first submission per (module, activity); reuse its schema for further entries. The ai object is REQUIRED (reasoning + model + confidence). If confidence < the activity's threshold, the transition is suppressed and the entry is flagged. Server-side guard rules (human/hybrid actor, state-change confirm, confidence-inflation) may block — see inistate://guardrails. Input shapes: ActivitySubmission in inistate://schema/runtime.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
aiYesREQUIRED — AI agent traceability
dueNoISO 8601
inputNoField values keyed by display name, as an object (never a JSON-encoded string). File/Image: {name,path}. Module: {id,value} (both required). User: {id,value,username} (all three required). Plural variants (Users/Modules/Files/Images): arrays of those objects. Location: {lat,lng,placeName} — lat/lng unquoted numbers, placeName the place's display name; never a combined "lat,lng" string. Table: an array of row objects keyed by sub-field name, e.g. [{"Item Code": "A-1", "Qty": 2}]. Number/Currency/Integer: JSON numbers, never strings, at the top level and inside Table rows. YesNo: true or false, never "yes". Text/MultilineText/Email: one string — join lines with \n, never an array. User/Module/Location shapes and YesNo/text value types are validated pre-flight — bare ids, bare strings, wrong value types, or objects missing any required key will be rejected.
stateNoTarget state name
moduleYes
commentNoOptional. Only when necessary to communicate with the user directly. Be concise; leave the detail in the fields.
entryIdNoOmit for create
activityNocreate
entryIdsNoFor bulk ops
assigneesNoUsernames
confirmedNoSet true only after explicit user authorization. Required for: changeStatus, state override, hybrid actor, retry after flag. Does not unlock human-actor activities. See inistate://guardrails.
workspaceIdNoWorkspace ID. Omit if set via env or set_workspace; required in stateless/remote mode.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.3.1
    • changedInput schema / properties / comment / description
      Previous value: -"Optional. Add only when it carries information not already in the field values or reasoning. Keep short and precise."New value: +"Optional. Only when necessary to communicate with the user directly. Be concise; leave the detail in the fields."
    • changedInput schema / properties / input / description
      Previous value: -"Field values keyed by display name. File/Image: {name,path}. Module: {id,value} (both required). User: {id,value,username} (all three required). Plural variants (Users/Modules/Files/Images): arrays of those objects. User/Module shapes are validated pre-flight — bare ids, bare strings, or objects missing any required key will be rejected."New value: +"Field values keyed by display name, as an object (never a JSON-encoded string). File/Image: {name,path}. Module: {id,value} (both required). User: {id,value,username} (all three required). Plural variants (Users/Modules/Files/Images): arrays of those objects. Location: {lat,lng,placeName} — lat/lng unquoted numbers, placeName the place's display name; never a combined \"lat,lng\" string. Table: an array of row objects keyed by sub-field name, e.g. [{\"Item Code\": \"A-1\", \"Qty\": 2}]. Number/Currency/Integer: JSON numbers, never strings, at the top level and inside Table rows. YesNo: true or false, never \"yes\". Text/MultilineText/Email: one string — join lines with \\n, never an array. User/Module/Location shapes and YesNo/text value types are validated pre-flight — bare ids, bare strings, wrong value types, or objects missing any required key will be rejected."
  2. First observedv1.1.1

TDQS

A4.5/5.0
Behavior5/5

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

Goes well past the annotations (destructive, non-idempotent, closed-world): it discloses confidence-threshold gating that suppresses the transition and flags the entry, server-side guard rules (human/hybrid actor, state-change confirm, confidence-inflation), and points to inistate://guardrails. That is exactly the mutation-risk context an agent needs before calling.

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?

Front-loads the core write semantics and the activity/ai requirements before the guardrail caveats. It is dense and clause-heavy, but nearly every clause (form-first, threshold suppression, guard rules, schema pointer) carries operational weight.

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?

For a 12-parameter, nested-object mutation tool with no output schema, it covers prerequisites, gating behavior, and where the input shapes live (inistate://schema/runtime). It does not describe what a successful submission returns, though the absent output schema limits how much that matters.

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 already 83%, so the baseline is 3; the description adds real meaning by explaining that `activity` holds data-driven standard or custom activity names (not hidden tools), that `ai` is mandatory with reasoning+model+confidence, and what happens when confidence falls below the activity's threshold.

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+scope: 'one call performs exactly one named activity on one entry of one module, and nothing else runs.' That scope statement implicitly separates it from the bulk sibling submit_activities and from read tools like get_entry, so an agent can route 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?

Gives concrete prerequisites: call get_form before the first submission per (module, activity) and reuse its schema, and use get_module_schema tier=extended to discover custom activity names. It stops short of naming submit_activities as the multi-entry alternative even though the schema exposes entryIds 'For bulk ops'.

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