Spin a random picker wheel, pick a random number, and search shared wheels from spinwheelnames.com.
Scored across 4 tools
get_wheel retrieves an existing saved wheel, spin_wheel creates/spins and saves a new wheel, and search_wheels finds public wheels, so those three are distinct. pick_random_number overlaps conceptually with spinning a numeric wheel, but its narrow scope makes it clear enough in practice.
All tool names use snake_case and follow a verb_noun pattern: get_wheel, pick_random_number, search_wheels, spin_wheel. This is highly predictable despite pick_random_number being slightly longer.
Four tools is well-scoped for a spin-wheel service: fetch, search, spin/save, and a simple random-number helper. Each tool has a clear purpose without redundancy.
The set covers fetching saved wheels, searching public wheels, spinning/saving new wheels, and random number picking. There is no update or delete operation for saved wheels, but for a lightweight public picker service this is a minor gap agents can work around.
Fetch a specific saved wheel from spinwheelnames.com by its slug or id, including its entries and description, and show it as an interactive wheel the user can spin.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The wheel slug or custom id (from a spinwheelnames.com URL). |
Pick a random whole number in an inclusive range, like spinning a "pick a number" wheel. Defaults to 1-100.
| Name | Required | Description | Default |
|---|---|---|---|
| max | No | Maximum value, inclusive. Defaults to 100. | |
| min | No | Minimum value, inclusive. Defaults to 1. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false and idempotentHint=false, so the safety and repeat-call behavior is covered structurally. The description adds the default range (1-100), which is useful, but says nothing about randomness quality, uniform distribution, or what the call returns.
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 with the core behavior front-loaded and the default appended. The wheel analogy is mildly decorative and overlaps a sibling's domain, but it costs little and aids intuition.
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 two-optional-parameter, side-effect-free tool with no output schema and full annotation coverage, the description supplies enough to invoke it correctly. Only the return shape and behavior on invalid ranges are unaddressed, which are minor gaps here.
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%, with both min and max documented as inclusive and given defaults, so the schema carries the parameter burden. The description only restates the inclusive range and default range, adding no syntax or edge-case semantics (e.g. what happens if min > max) beyond 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?
The description gives a specific verb+resource ("pick a random whole number") plus scope ("inclusive range") and a default (1-100), so the effect is immediately understandable. It does not explicitly differentiate itself from the sibling spin_wheel, and the "like spinning a wheel" analogy actually overlaps with that sibling's vocabulary, which slightly muddies rather than sharpens the distinction.
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?
There is no guidance on when to use this rather than spin_wheel or get_wheel, and no exclusions or prerequisites. The agent must infer from the name and analogy that this is the no-wheel number generator.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search publicly shared name-picker wheels already created on spinwheelnames.com by title or description (e.g. "classroom", "baby names", "raffle"). Returns links a user can open to view or reuse an existing wheel.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (1-20, default 5). | |
| query | Yes | Search text to match against wheel titles and descriptions. |
Spin a random picker wheel over a list of entries (names, teams, prizes, tasks, anything) and return the winner. Use this whenever a user wants a fair, random pick from a list, or wants a wheel to spin. Shows an interactive wheel the user can spin again, and saves it on spinwheelnames.com so the returned url opens and shares that exact wheel. Always give the user the url.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional short title for the wheel, e.g. "Who presents first?". | |
| entries | Yes | The list of names/entries to spin the wheel over (at least 2). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only say this is not read-only, not idempotent and not destructive. The description adds real behavioral context beyond that: it renders an interactive wheel and persists it to spinwheelnames.com, returning a public shareable URL. It does not state whether saved wheels are permanent/deletable or whether the URL is publicly accessible to anyone, which is the main undisclosed trait. (Saving to the service's own site is presumably in-world, so no annotation contradiction.)
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-loads what the tool does and the trigger for using it, then adds the side effect and return value. Slightly long and includes an output instruction ('Always give the user the url'), but every sentence carries 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 correctly explains what comes back (a winner plus a URL that opens and shares the exact wheel) and covers the persistence side effect. It leaves open the sharing/permanence semantics of the saved wheel, but is otherwise sufficient 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?
Schema description coverage is 100% and both parameters are documented there (entries, minItems 2, title). The description adds only illustrative entry types ('names, teams, prizes, tasks, anything'), which is mild value over the schema, so the 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 (spin) and resource (random picker wheel) with scope ('over a list of entries') and outcome ('return the winner'). This is enough to separate it from pick_random_number (a non-list random draw) and from search_wheels/get_wheel, which do not create a spin.
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 triggering context: 'Use this whenever a user wants a fair, random pick from a list, or wants a wheel to spin.' It does not name the alternative tools or state when NOT to use it (e.g. picking a bare random number), so it stops short of explicit routing.
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.
search_wheels1 field changedInput schema / properties / query / descriptionPrevious value: -"Search text to match against wheel titles."New value: +"Search text to match against wheel titles and descriptions."spin_wheel1 field changedInput schema / properties / titleAdded value: +{
+ "description": "Optional short title for the wheel, e.g. \"Who presents first?\".",
+ "type": "string"
+}get_wheelpick_random_numbersearch_wheelsspin_wheelFair random picks with the wheel in your chat: pick names, split teams, run certified draws.
Fair, reproducible randomness for agents: dice, coins, integers, list picks, shuffles, with seeds.
Real local places, events, and movie/TV picks, plus decision-maker games (wheel, dice, bracket).
Search Wikipedia, read summaries and full text, target sections, find nearby pages, list languages.
Add one secure layer between your agents and this server.
