Draw names for Secret Santa without sign-ups or email addresses.
Scored across 2 tools
The two tools target clearly distinct game formats: Secret Santa name drawing versus White Elephant turn-order/rules planning. Their descriptions explicitly cross-reference each other with 'do not use' guidance, eliminating ambiguity despite sharing the gift-exchange domain.
Both tool names follow the same predictable plan_<game> pattern: plan_gift_exchange and plan_white_elephant. The verb and noun structure is fully consistent across the set.
Two tools is slightly below the typical 3–15 range, but each tool represents a broad, well-defined workflow rather than a trivial operation. The count is reasonable for a narrowly scoped gift-exchange planning server with exactly two supported game types.
The surface covers the core planning needs for both Secret Santa and White Elephant, including exclusions, rules, PDFs, and private reveal links. Minor gaps exist around post-generation modifications or resending, but these are partially mitigated by the tool outputs and the server's explicitly stateless design.
Use this when the user wants to draw names for a Secret Santa or gift exchange (secret santa generator, name draw, no email needed), including exclusions such as couples, households, "Ana can't draw Bo", or last year's pairs, an optional no 2-person loops rule, a budget, an exchange date, wish lists, and an organizer note. Returns one private reveal link per participant plus copy-ready messages; each pairing is encrypted inside the link, so the result never shows who drew whom. Explains exactly why when no valid draw exists. Handles 3 to 60 people. Does not send emails or texts and does not store anything. Do not use for White Elephant or Yankee Swap games (use plan_white_elephant) or for picking one random winner.
| Name | Required | Description | Default |
|---|---|---|---|
| budget | No | Gift budget as the group says it, e.g. $30, 25 EUR, or £20-£25. | |
| language | No | Language of the reveal pages and share messages: en, es, fr, de, pl, pt, or ja (e.g. pl). Default en. | |
| event_name | No | Name of the exchange shown on every link, e.g. Office Holiday Party 2026. | |
| exclusions | No | One-way rules such as "Ana can't draw Cy" or last year's pairs, e.g. [{"giver":"Ana","cannot_draw":"Cy"}]. Cy may still draw Ana unless a second rule says otherwise. | |
| households | No | Couples or households whose members must not draw each other (both directions), e.g. [["Ana","Bo"],["Cy","Dee","Eli"]]. | |
| wish_lists | No | Optional wish lists. Each one is shown only to the person who draws that participant. | |
| participants | Yes | Everyone taking part (3 to 60 people), e.g. ["Ana","Bo","Cy","Dee","Eli","Fay"]. Names must be unique; add a last initial to tell two people with the same name apart. Any language or script works. | |
| exchange_date | No | Gift exchange date as YYYY-MM-DD, e.g. 2026-12-18. | |
| organizer_note | No | Optional note shown on every reveal page, e.g. Wrap gifts and bring them to the kitchen by 3 pm. | |
| no_two_person_loops | No | true = never let two people draw each other (no A gives to B while B gives to A). Default false. | |
| include_organizer_list | No | true only when the organizer explicitly asks to see every pairing; adds a link to the full list, which spoils the surprise for them. Default false. |
| Name | Required | Description |
|---|---|---|
| mode | Yes | |
| rules | Yes | |
| budget | Yes | |
| language | Yes | |
| sampling | Yes | |
| warnings | Yes | |
| downloads | Yes | |
| draw_code | Yes | |
| event_name | Yes | |
| exclusions | Yes | |
| households | Yes | |
| participants | Yes | |
| exchange_date | Yes | |
| message_template | Yes | |
| valid_arrangements | Yes | |
| exchange_date_label | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-destructive read (readOnlyHint=true, destructiveHint=false), and the description adds genuinely new behavioral facts: one private reveal link per participant, encrypted pairings never shown to the caller, copy-ready messages, explicit explanation when no valid draw exists, 3-60 person bounds, no email/text sending, and no storage. Nothing contradicts idempotentHint=false (the draw is randomized).
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 'Use this when...' trigger and then packed with decision-relevant facts; no filler sentences. The opening sentence is long and list-heavy enough that a reader may need a second pass, which keeps it just short of a 5.
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?
Despite an 11-parameter tool, the description covers constraints (3-60 people, unique names), failure behavior (explains why no valid draw exists), side effects (no emails, no storage), and the shape of the output in user terms (private links plus copy-ready messages). An output schema exists, yet the description still tells the agent what the caller will and will not see.
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 the schema already documents every parameter and the baseline is 3. The description adds value by framing the domain vocabulary an agent will encounter in user requests—'couples' and 'households' map to one input while 'Ana can't draw Bo' and 'last year's pairs' map to another, and 'no 2-person loops' is called out by name—which helps translate intent into the right field.
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 concrete verb and resource ('draw names for a Secret Santa or gift exchange') and enumerates the concrete capabilities: exclusions, households, no-two-person-loops, budget, date, wish lists, organizer note. It explicitly distinguishes itself from plan_white_elephant and from a random-winner picker, so an agent can select it without opening either schema.
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 explicit selection criteria ('Use this when the user wants to draw names for a Secret Santa') plus explicit exclusions ('Do not use for White Elephant or Yankee Swap games (use plan_white_elephant) or for picking one random winner'). The named alternative removes any ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this when the user wants to run a White Elephant, Yankee Swap, or Dirty Santa gift game: shuffles a fair random turn order for 3 to 60 players and writes the rules (steal limit per gift, optional cap on steals per turn, no immediate steal-backs, player 1's final swap), with a printable PDF (Letter or A4) that includes a gift tracker and a printable web page. Does not run the game live or track steals. Do not use for Secret Santa name draws (use plan_gift_exchange).
| Name | Required | Description | Default |
|---|---|---|---|
| paper | No | PDF paper size: letter (default) or a4, e.g. a4. | |
| budget | No | Gift budget, e.g. $25. | |
| event_name | No | Name printed on the rules sheet, e.g. Team White Elephant 2026. | |
| party_date | No | Party date as YYYY-MM-DD, e.g. 2026-12-12. | |
| steal_limit | No | How many times one gift can be stolen before it is frozen, e.g. 3 (default). 0 turns stealing off. | |
| participants | Yes | Everyone playing (3 to 60 people), e.g. ["Ana","Bo","Cy","Dee","Eli","Fay","Gus","Hal"]. Names must be unique. | |
| max_steals_per_turn | No | Optional cap on steals in one turn's chain, e.g. 2. Omit for no cap. | |
| first_player_final_swap | No | true (default) = player 1 gets a final turn to swap with any unfrozen gift, since they never had a chance to steal. | |
| no_immediate_steal_back | No | true (default) = you cannot steal back the gift that was just taken from you. |
| Name | Required | Description |
|---|---|---|
| mode | Yes | |
| rules | Yes | |
| budget | Yes | |
| warnings | Yes | |
| downloads | Yes | |
| event_name | Yes | |
| party_date | Yes | |
| turn_order | Yes | |
| steal_limit | Yes | |
| party_date_label | Yes | |
| max_steals_per_turn | Yes | |
| first_player_final_swap | Yes | |
| no_immediate_steal_back | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real context beyond that: the shuffle is a 'fair random turn order' (consistent with idempotentHint=false), and the artifacts are a printable PDF in Letter or A4 with a gift tracker and printable web page. It does not discuss pagination, output limits, or what happens with out-of-range inputs, so it stops short of full transparency.
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?
The trigger condition and the sibling exclusion are front-loaded, and no sentence is padding. The drawback is that the core content is delivered as one very long clause-heavy sentence, which is denser than it needs to be — splitting the rule set from the output artifacts would read faster.
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 values need no explanation. With nine parameters, a sibling to route against, and a mutation-adjacent feel, the description covers the trigger, the exclusions, the artifacts produced, and the game-rule options that matter for correct invocation. Nothing an agent needs in order to choose and call this tool is missing.
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 baseline is 3; the description earns above that by explaining the rule semantics the parameter names alone don't convey — steal limit per gift, optional cap on the steal chain per turn, no immediate steal-backs, and player 1's compensatory final swap — plus the 3-to-60 player bound and Letter/A4 paper choice. It does not touch budget, party date, or event_name, but those are self-evident from the schema.
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 — shuffles a random turn order and writes rules plus a printable PDF — and names the game variants (White Elephant, Yankee Swap, Dirty Santa) it covers. It also explicitly names the sibling plan_gift_exchange as out of scope, so an agent can distinguish the two without opening either schema.
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?
Opens with an explicit 'Use this when the user wants...' trigger, then adds a negative boundary ('Does not run the game live or track steals') and a concrete alternative for the nearby-but-wrong case ('Do not use for Secret Santa name draws (use plan_gift_exchange)'). When-to-use, when-not-to-use and the replacement tool are all spelled out.
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.
plan_gift_exchangeplan_white_elephantOrganise a Secret Santa from Claude or ChatGPT. Matchings never appear in the chat.
Create a Secret Santa party with names, emails, a date, a place, and a budget.
Find a time a group can meet: no-login availability poll that picks the best meeting slot.
Run transparent giveaways on Instagram, X, TikTok and YouTube posts. Draw in your browser.
Add one secure layer between your agents and this server.
