Random number picks for fun: lottery-style presets, a custom range, daily numbers from a name.
Scored across 1 tool
There is only one tool, so an agent cannot misselect. Its purpose (generating lottery-style random picks, either seeded or custom) is clearly stated and self-contained.
A single snake_case name, lucky_numbers, is clear and matches the server's purpose. No convention mixing is possible with one tool.
One tool is borderline thin for a tool set, though the server's scope is genuinely singular and the tool itself covers several presets and a custom mode. It does not feel under-designed, just minimal.
The single tool covers the full surface: preset lotteries, custom min/max/count picks, and an optional deterministic daily seed with a required disclaimer note. The only minor gap is that repeated seeded looks within a day and date rotation are implicit rather than exposed as separate controls.
Random number picks for fun, like an "I'm feeling lucky" button. Presets: powerball (5 of 1-69 plus 1 of 1-26), mega_millions (5 of 1-70 plus 1 of 1-24), euromillions (5 of 1-50 plus 2 Lucky Stars of 1-12), uk_lotto (6 of 1-59), or custom with min, max and numbers. Give seed_text (a name or a birthday) for one set of numbers that stays the same for that text all day (UTC) and changes the next day. This is entertainment only: it predicts nothing, every combination has exactly the same odds, and no pick improves the chance of winning. Always show the user the note field with the numbers.
| Name | Required | Description | Default |
|---|---|---|---|
| max | No | custom only: the highest number. | |
| min | No | custom only: the lowest number. | |
| date | No | Only with seed_text: the UTC day (YYYY-MM-DD) to draw for. Defaults to today. | |
| game | Yes | Which ball set to draw from. custom needs max, and takes min and numbers. | |
| count | No | How many lines (sets of numbers) to draw. | |
| numbers | No | custom only: how many different numbers per line. | |
| seed_text | No | Optional text such as a name or a birthday. The same text gives the same numbers all day. It is not stored. |
| Name | Required | Description |
|---|---|---|
| date | No | |
| game | No | |
| mode | No | |
| note | Yes | |
| error | No | |
| lines | No | |
| title | No | |
| bonusLabel | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, non-destructive, non-idempotent behavior; the description adds the crucial nuance that results are random on each call unless seed_text is supplied, in which case the same text yields the same numbers for the whole UTC day. It also discloses that seed_text is not stored and instructs the agent to surface the note field, both real behavioral context rather than restating annotations.
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?
Purpose and presets are front-loaded in the first sentence and the whole thing is three tight sentences. The entertainment disclaimer is slightly redundant ('predicts nothing', 'same odds', 'no pick improves the chance' all say the same thing), which keeps it from 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?
For a small read-only generator with a full schema, complete parameter descriptions, an output schema, and honesty annotations, the description covers the remaining agent-relevant gaps: mode selection, seeding behavior, non-persistence of the seed, and the need to surface the note field.
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 every parameter including min/max/numbers/date/seed_text semantics is already documented. The description reinforces the custom-mode dependency and the seed_text/day relationship but adds little beyond what the schema states, 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 and resource ('random number picks') plus the exact preset families supported (powerball, mega_millions, euromillions, uk_lotto, custom) with their ball ranges. An agent knows precisely what it will get back: lottery-style draws or a custom-range draw.
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 operational context: use presets or custom, give seed_text for a stable daily set, and it explicitly frames the tool as entertainment-only that 'predicts nothing' — a strong cue that it should not be invoked for real forecasting. It stops short of explicit exclusion conditions or routing to alternatives (there are no siblings), so not quite a 5.
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.
lucky_numbersLottery picks in any format, past draws, ticket check, and a link for numbers drawn from a sentence.
Spin a random picker wheel, pick a random number, and search shared wheels from spinwheelnames.com.
Generate random values and probability distribution samples.
Fair, reproducible randomness for agents: dice, coins, integers, list picks, shuffles, with seeds.
Add one secure layer between your agents and this server.
