Skip to main content
Glama

TT Uni Plan Sessions

tt_uni_plan_sessions

The session calendar: plan a live batch's sessions on Tradetron's Zoom and see what is already taken. ONLY action=create WRITES (it adds the sessions to the cohort and books their meetings); availability and preview only read and change nothing. action = - availability: cohort_id (+ from_date "YYYY-MM-DD", days 1-70, default today + 42). Per licensed Zoom seat, what is busy (start, end, why: a free webinar, another course's batch), plus this batch's own sessions. A time is unavailable only when EVERY seat is busy. Each session also holds its seat 15 min before and 60 min after. - preview: cohort_id + dates ["YYYY-MM-DD", ...] OR pattern {from "YYYY-MM-DD", weekdays ["mon", ...] (default Mon-Fri), count | until} + time "HH:MM" IST + minutes (+ topics [one per session] | topic). Answers each session free or clashing, with the nearest free times, and the one seat free for all of them. Creates nothing. - create: the same input; creates ALL the sessions (only a past date or sessions overlapping each other refuse, and then NONE go in). A clash with Tradetron's Zoom NEVER refuses: the teacher's dates stay, Tradetron buys one more Zoom seat (waiting_for_seat: true; staff are mailed, the seat is taken automatically once it is in). Offer the suggested free times as a choice, never as a condition. The batch's dates follow. Before approval the seat is HELD for those sessions (14 days, then until the batch ends once approved) so no other course can take it; the Zoom meeting itself is made on that seat when enrolment opens. A batch with its own pasted join_url never holds or books Tradetron's Zoom. Course 94's dates (10-14 Nov Tue-Sat, 16-20 Nov Mon-Fri, 19:00) are one pattern: from 2026-11-10, weekdays mon..sat, count 10. Always preview, show the teacher the clashes and suggestions, then create. Recordings arrive by themselves only from Zoom meetings on Tradetron's Zoom account with cloud recording on: the batch meeting TT Uni books, a session's own booked meeting, or a pasted link to a meeting on that account. A recording is matched by the meeting number in the link (zoom.us/j/) and by time: it must start between 60 minutes before the session and 180 minutes after its scheduled end. A pasted link to a meeting on any other Zoom account is never picked up: add that recording with tt_uni_session_recording (action=add, a link). With record_sessions false nothing is recorded or offered.

TT Uni is Tradetron's course marketplace (tradetron.tech/learn). These tools act as the signed-in user and work only for approved TT Uni teachers; anyone else is pointed to https://tradetron.tech/learn/teach. DRAFTS ONLY: nothing is published until the TT Uni review team approves the course. TT Uni teaching rules: no tips or buy/sell calls; no promised returns and no P&L screenshots as proof; any market data shown must be at least 30 days old; disclose any paid strategy of your own that the course mentions. Prices are in INR and exclude GST (18% is added at checkout); the teacher earns 50% of the price. AUTH-REQUIRED.

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": {
      "action": "<action>",
      "cohort_id": "<cohort_id>"
    },
    "name": "tt_uni_plan_sessions"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoavailability: how many days, 1-70
timeNopreview/create: start, HH:MM IST
datesNopreview/create: single days, YYYY-MM-DD (IST)
topicNopreview/create: one topic for all, numbered
actionYesavailability | preview | create
topicsNopreview/create: one topic per session; fewer = the rest numbered
minutesNopreview/create: length, 5-600
patternNopreview/create: {from, weekdays, count | until}
cohort_idYes
from_dateNoavailability: first day, YYYY-MM-DD

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description supplies the whole behavioral picture. It discloses transactional atomicity ("only a past date or sessions overlapping each other refuse, and then NONE go in"), the non-refusal seat-purchase path with waiting_for_seat, the 14-day seat hold, when the Zoom meeting is actually created, and the pasted join_url exception. It also flags auth requirements and the drafts-only approval gate. Nothing here contradicts the annotations; destructiveHint=false is consistent with clash handling that never refuses.

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

Conciseness2/5

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

The purpose and action breakdown are front-loaded and well ordered, but roughly a third of the text is unrelated to invoking this tool: Zoom recording matching windows, GST and 50% revenue split, and the TT Uni teaching rules (no tips, no promised returns, 30-day-old market data). Those belong to other tools or to policy documentation and dilute the operative instructions an agent needs mid-call. The core content is compressed well; the surrounding payload is not.

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 10 parameters and no output schema, the description carries the return burden and does so: availability yields per-seat busy intervals and a 15-min-before/60-min-after hold, preview yields free-or-clashing plus nearest free times and a common seat. Refusal conditions, seat-hold lifecycle, and auth eligibility are all covered. Padding with marketplace policy slightly blurs the actionable core, but nothing an agent needs to call it correctly is 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?

Schema coverage is already 90%, so the bar is high, but the description adds the one structural fact the schema does not convey: dates and pattern are alternatives, not complements. It also restates the operative defaults (weekdays Mon-Fri, days default today+42, YYYY-MM-DD IST) in the context of each action, which reduces mis-invocation risk. The rest largely mirrors the schema descriptions, so it is an increment rather than a transformation.

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 and resource: "plan a live batch's sessions on Tradetron's Zoom and see what is already taken." It then decomposes the tool into three named actions (availability, preview, create) and states unambiguously that only create writes. An agent can tell this apart from tt_uni_save_session or tt_uni_session_recording without opening any schema.

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?

Explicit routing between the tool's own modes: read-only availability/preview vs writing create, with the parameter shapes each mode expects. It goes further and prescribes a workflow ("Always preview, show the teacher the clashes and suggestions, then create") and an interaction norm ("Offer the suggested free times as a choice, never as a condition"). That is when-to-use guidance of an unusually high standard.

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