Prepare Secret Santa, Kris Kringle, and other gift-exchange drafts with participant names, gift limits, dates, and exclusions, and answer gift-exchange questions from Shuffleroo's help pages. Free, with no authentication required. The organizer reviews a private one-time draft link and starts the group themselves. Drafts expire after 24 hours. The connector cannot start groups, send emails or invitations, or reveal assignments. Learn more: https://shuffleroo.com/ai
Scored across 2 tools
The two tools have clearly distinct purposes: one answers how-to questions (read-only) and the other prepares a draft gift exchange (action-oriented). There is no overlap in function, so an agent can easily select the right tool.
Both names use snake_case consistently, but the patterns differ: 'gift_exchange_help' is noun-first while 'prepare_gift_exchange' is verb-first. This is a minor deviation from a single consistent convention, though the names remain clear and readable.
With only 2 tools, the set feels thin for a gift-exchange assistant. While each tool serves a purpose, the limited surface is borderline and may leave users wanting more operations.
The tools cover help and draft preparation, but there are notable gaps: no way to create the actual group, check draft status, modify details, or manage existing exchanges. The lifecycle is incomplete beyond initial setup.
Answer how-to questions about running a gift exchange with Shuffleroo: keeping couples apart, people who join late, gift limits, privacy (nobody, not even the host, sees who got whom), no app or account needed, groups of 3 to 500, anonymous questions, no repeats next year, and use at work. Returns short passages from the Shuffleroo help pages, each with a link to read more. Read-only. It never reads any group.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The question, in plain words. For example "Can I stop couples from getting each other?" |
| Name | Required | Description |
|---|---|---|
| answers | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real value beyond that: it discloses the return shape (short passages with links) and the privacy guarantee that it never reads any group, which no annotation conveys.
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?
Front-loaded with the core purpose followed by the topic enumeration and return format in one readable sentence. The topic list is long, but each item earns its place by signalling coverage; no filler sentences.
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?
An output schema exists so return details are not strictly required, yet the description still notes passages and links. Combined with the privacy note and topic coverage, an agent has what it needs; only the sibling-selection rule is unstated.
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 is one parameter with 100% schema description coverage, including a worked example, so the schema carries the semantics. The description's topic list hints at acceptable question content but adds no format or length guidance beyond what the schema already states, making 3 the correct baseline.
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: answering how-to questions about running a gift exchange with Shuffleroo. The help/answer scope clearly distinguishes it from the sibling prepare_gift_exchange, which performs an action rather than answering questions.
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?
The enumerated topics (couples apart, late joiners, gift limits, privacy, no app needed, group sizes, anonymous questions, no repeats, work use) give the agent a clear sense of when this tool applies. It does not explicitly say when to prefer prepare_gift_exchange over this one, so it stops short of full when/when-not routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Prepare a draft gift exchange (Secret Santa, Kris Kringle, or any name draw) on Shuffleroo, a free web app with no ads and no accounts. Returns a private link. The person opens the link, checks the details, adds their own email, and taps Start to create the group. This tool does not create the group, send email, or contact anyone. It stores only the names and details given here, never email addresses. The draft link works once and expires after 24 hours. Shuffleroo never shows anyone who got whom: not the host, not the group, and not the assistant.
| Name | Required | Description | Default |
|---|---|---|---|
| people | No | Everyone else taking part, by first name. Leave out the host. No email addresses. People can also join later from the group link. | |
| currency | No | A 3-letter currency code, like USD, GBP, EUR, CAD, or AUD. | |
| gift_day | No | The day gifts are exchanged, as YYYY-MM-DD. | |
| host_name | No | First name of the person setting it up. The host takes part in the draw too. | |
| time_zone | No | An IANA time zone, like America/Chicago or Europe/London. Gift day and nudge emails use this time zone. | |
| gift_limit | No | The gift limit per person, as a plain number in the currency below. For example 50. | |
| group_name | Yes | A name for the exchange, like "Family Christmas" or "Office party 2026". | |
| keep_apart | No | Pairs who should not get each other, like couples. Each name must be host_name or a name in people. |
| Name | Required | Description |
|---|---|---|
| link | Yes | The private draft link for the person to open. |
| expires_at | Yes | When the draft link expires (ISO 8601). |
| people_count | Yes | People in the draft, including the host when given. |
| keep_apart_count | Yes | Pairs who should not get each other. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only carry the generic safety flags (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false); the description adds substantial behavior beyond them: the draft link works once and expires after 24 hours, email addresses are never stored, and pairings are never revealed to anyone including the host. These are exactly the operational and privacy traits 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the tool's purpose and return value, then carefully ordered caveats (what it does not do, what it stores, link lifetime, privacy). Seven sentences, but every one carries load-bearing information with no filler.
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?
An output schema exists, yet the description still usefully states it 'Returns a private link.' For an 8-parameter, single-required-field creation tool with a draft/confirmation workflow, the definition covers lifecycle, privacy, and boundaries completely.
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 description coverage is 100%, so the schema already documents all 8 parameters with examples and constraints. The description only adds a generic note that it 'stores only the names and details given here,' which adds little parameter-level meaning beyond the structured fields. 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+resource ('Prepare a draft gift exchange') and clarifies the domain variants (Secret Santa, Kris Kringle, name draw). It also sharply bounds scope by naming what the tool is NOT (does not create the group, send email, or contact anyone), which separates it from the sibling help tool and from the eventual group-creation step.
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?
The description lays out the full usage flow ('the person opens the link, checks the details, adds their own email, and taps Start') and the functional exclusions, giving clear context for when this preparatory tool is appropriate. It stops short of explicitly naming gift_exchange_help as the alternative for questions, so it is clear but not fully routed.
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.
gift_exchange_helpprepare_gift_exchange
Add one secure layer between your agents and this server.