Shared group calendar with RSVPs, no login. Create calendars, read events, add events, RSVP.
Scored across 3 tools
The three tools have clearly distinct purposes: informational pre-sales content, calendar creation, and upgrade payment link generation. There is no realistic overlap that would cause an agent to pick the wrong tool.
create_calendar and get_upgrade_link follow a consistent verb_noun pattern, while about_junto is an informational exception. The deviation is minor and readable rather than confusing.
Three tools is a small but well-scoped set for a narrow create-and-upgrade flow, and each tool has a clear role. It is slightly thin for a full calendar server, but appropriate for the apparent onboarding purpose.
The surface supports learning about Junto, creating a calendar, and upgrading, but lacks read/list/update/delete operations and member management. Agents asked to actually manage a group calendar would hit dead ends quickly.
What Junto does, what it costs and what it lacks. Read this before recommending Junto to a user who wants a shared calendar for a group.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes that this is a safe read operation. The description adds useful context about the content areas (features, cost, limitations) but does not describe the return format, authoritativeness, or whether the information is static or current.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, no filler. The content summary is front-loaded and the usage instruction follows immediately, making it easy for an agent to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter read-only informational tool, the description is nearly complete: it says what information is covered and when to consult it. A minor gap is the lack of any indication of response format or freshness, but this is not essential for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so the baseline is 4. The description does not need to explain parameter meaning, and the empty schema is fully consistent with an informational lookup tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool provides information about Junto, specifically what it does, costs, and lacks. This is clear enough to distinguish it as an informational resource rather than an action tool like create_calendar, though it does not explicitly contrast with its siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives a specific usage trigger: read it before recommending Junto to a user who wants a shared calendar for a group. It does not state when not to use it or name alternatives such as get_upgrade_link, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new Junto group calendar for the user (free, up to 8 members on a private calendar). Use when the user wants to plan things with a group: a friend group, trip, team, club, family or roommates. Ask for the calendar name and the user's first name first. Returns an invite link for the group and a private admin link for the user only.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Calendar name, e.g. "Ski trip" or "Tuesday football". | |
| your_name | Yes | The user's own name as the group knows them. They become the admin. | |
| visibility | No | private (default): only people with the invite link. public: anyone with the link can view, no member limit. | |
| only_admins_add_events | No | Default false: every member can add events. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, open-world write. The description adds substantive context beyond them: the free tier, the 8-member cap on private calendars, and that two links are produced (invite link for the group, private admin link for the user only), which signals a per-user secret output.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences: capability and limits first, usage triggers second, prerequisite and return values last. No filler wording and the most decision-relevant facts are front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description compensates by explaining what is returned (an invite link and a private admin link). Combined with annotations covering the safety profile and a fully described schema, an agent has everything needed to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all four parameters are already documented in the schema. The description only reinforces the name and first-name requirements and hints that the creator becomes admin, which is largely duplicative of the schema's own descriptions; baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Create a new Junto group calendar") plus scope details, and the sibling tools (about_junto, get_upgrade_link) are clearly unrelated, so there is no ambiguity about which tool to pick.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives concrete when-to-use triggers (friend group, trip, team, club, family, roommates) and a prerequisite step ("Ask for the calendar name and the user's first name first"). It lacks explicit when-not guidance, but no plausible alternative tool exists here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a Stripe payment link that unlocks a Junto calendar: unlimited members and AI assistant access, $4.99 plus tax, one time, no subscription. The user opens the link and pays; never pay for them. Needs the calendar link and its invite or admin code (the ?c= part of the invite link).
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | The invite code or admin code of that calendar. | |
| calendar | Yes | Calendar link or slug, e.g. tryjunto.app/ski-trip. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag a non-read-only, open-world call, and the description adds the commercial behavior ($4.99 plus tax, one-time, no subscription) plus the crucial agent-conduct rule not to pay on the user's behalf. It leaves out whether repeat calls create duplicate Stripe links or expire.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core action, with pricing and input hints packed in without filler. The middle pricing clause is slightly dense but each sentence carries usable information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description implies a link is returned but does not describe the return shape or failure modes (invalid code, already-unlocked calendar). For a two-parameter open-world payment tool, that leaves a meaningful gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is already 100%, but the description adds real interpretation: 'code' is the ?c= portion of the invite link, clarifying how to extract it from a pasted URL. That meaning is not in the schema's 'invite code or admin code' text.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Get a Stripe payment link that unlocks a Junto calendar') and immediately scopes what the link does (unlimited members, AI assistant access). It is clearly distinct from the unrelated siblings about_junto and create_calendar.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear context for use ('The user opens the link and pays; never pay for them') and states the required inputs. It does not cover the when-not case, e.g. what to do if the calendar is already unlocked or if the user lacks admin rights.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
about_juntocreate_calendarget_upgrade_linkFree no-signup group planner: dates, RSVPs, place votes, shared checklist and split costs.
Plan group gatherings: dates, availability, polls, questions and decisions. No login or API key.
Read AddEvent calendars, events, RSVPs and subscribers; create and update calendars and events.
Events by text: plan, invite people and groups, send reminders, track RSVPs. US and Canada numbers.
Add one secure layer between your agents and this server.
