Lottery Numbers

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely useful behavioral detail beyond them: kr645 returns rank and prize per winner from the official record, while powerball/megamillions return only the match and omit prize amounts due to state/multiplier variance.

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 tightly packed sentences, front-loaded with the core action and then the per-game output semantics. No filler or restated boilerplate.

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 carries the return-value burden and does explain the key differences per game (rank+prize vs match only). It stops short of describing the actual response structure/field names, but covers the decision-relevant behavior.

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 high (75%) and the numbers/extra_number constraints are already documented there. The description still adds meaning the schema lacks: the draw parameter defaults to the latest draw when omitted, which the schema only gestures at with 'Optional, as in get_draw.'

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 action ('Compare your numbers with a draw') with the resource (a draw) and notes the default scope ('the latest unless you give one'). It is clearly distinguishable from siblings get_draw and pick_numbers, and even differentiates the per-game behavior in the same breath.

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?

Usage is implied rather than stated: an agent can infer you check tickets after obtaining numbers, and the reference to get_draw hints at the relationship. There is no explicit when-to-use/when-not or routing guidance relative to get_draw or pick_numbers.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description usefully adds data provenance (dhlottery.co.kr, data.ny.gov), which is genuine extra context, but it says nothing about behavior on an invalid draw number/date or what the response contains.

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 compact sentences, front-loaded with what is returned, then the argument format, then sources. No filler; every clause 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 states what is returned and how the single required enum plus optional draw argument behave. That covers everything an agent needs to invoke this simple read tool 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 only 50% (the game enum has no schema description), and the description compensates by mapping each enum value to its required argument form and its source. It adds real semantics beyond the schema, though it largely restates the draw field's own description.

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 ('the winning numbers of the latest draw, or of one past draw') with clear scope. It is implicitly distinguishable from check_ticket and pick_numbers, but the description never names or contrasts with those siblings, so the differentiation is left to inference.

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 conditional usage for the optional draw argument ('kr645: give the draw number (회차). powerball, megamillions: give the draw date YYYY-MM-DD') and explicitly says 'Leave it out for the latest.' That is strong how-to-use guidance, but there is no when-to-use-this-vs-siblings advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=false, so safety is covered. The description adds genuinely new behavior: the response carries a seed, and re-supplying that seed reproduces the identical draw ("that is how a draw is checked"), which is the key non-obvious trait given idempotentHint=false.

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 is front-loaded in the first clause, then the named-game list and the custom path follow logically. The game enumeration is long but earns its place because the schema only provides bare enum keys with no explanation of what each game means.

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 an 8-parameter tool with no required fields and no output schema, the description covers both invocation modes, the meaning of every enum, and the seed round-trip. What is missing is the concrete shape of the returned answer (how sets are grouped, field names) beyond the seed mention.

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?

With 88% schema coverage the baseline is 3, but the description goes further: it decodes each enum value (kr645 = Lotto 6/45 South Korea, etc.), spells out the min/max/count custom contract, and clarifies that extras are bonus balls drawn apart from 1 to extra_max. It also notes game may be omitted when count and max are given, a schema gap the schema itself does not state.

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 action (produce random numbers) on a specific resource (a named lottery game or custom format), which separates it from the retrieval siblings get_draw and check_ticket. It never explicitly names those siblings, so an agent must infer that this tool generates rather than looks up draws.

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 thoroughly explains the two usage modes (named game vs game='custom' with count/max), which is real guidance, but it says nothing about when to reach for this tool versus get_draw or check_ticket, nor about prerequisites. Usage is implied rather than contrasted with alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds the one behavior an agent could not guess: the tool returns no number, only a link the human must tap, and the agent must pass it on. It does not address whether repeated calls yield the same link, which matters given idempotentHint=true.

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: identity first, then the surprising mechanism, then the required agent action. No padding, and the link-not-number fact is front-loaded where it counts.

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 no-parameter, no-output-schema tool, the description supplies everything needed to call it and hand off correctly, including what comes back and what to do with it.

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?

Zero parameters, so there is nothing to disambiguate; baseline 4 applies. The description correctly adds no parameter detail because none exists.

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+resource: it draws a 'personal two-digit number' from the Prismtect prism, and makes clear it returns a link rather than the number. That implicitly separates it from siblings like random_integer and flip_coin, which hand back values directly, but no sibling is named.

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 user-intent triggers ('a lucky number, a number of their own or a number for today'), which is strong context for picking this over random_integer. It stops short of stating when NOT to use it or naming the plain-random alternative for users who just want any number.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing the deferred execution model (drawing happens on prismtect.com after the user opens the link), the 30-day link lifetime, and hard limits (max 8 numbers, max value 99, min 0 or 1). These are exactly the facts an agent needs to set user expectations and avoid assuming a number payload is returned; consistent with openWorldHint=true and readOnlyHint=false.

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?

Four sentences, front-loaded with the user intent and the output type, then supporting constraints. The range sentence largely duplicates schema constraints and could be trimmed, but nothing is confusing or padded.

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 fills that gap by saying the return value is exactly one prismtect.com link plus its lifespan. For a 7-parameter tool with full schema coverage, the remaining gap is minor — it doesn't cover error cases (e.g., conflicting game vs. custom fields) or whether identical sentences yield link reuse.

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% and the property descriptions already explain game, custom count/max, and extras. The description restates the grouping ('a game, or custom count and max with optional extras') and repeats the ranges, adding synthesis but no format-level detail the schema does not already supply. Baseline 3 is appropriate when the schema carries the parameter burden.

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: it produces a single prismtect.com link that draws lottery numbers from the user's own sentence. It explicitly distinguishes its own role from the drawing step ('this tool makes no numbers'), which separates it from siblings like pick_numbers or prismtect_number that presumably return numbers directly.

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 the exact user intent that selects this tool ('a user who wants lottery numbers drawn from a sentence of their own'), and the 'this tool makes no numbers' line clarifies when to prefer the link route over a number-returning sibling. It stops short of naming alternatives such as pick_numbers or prismtect_number explicitly, so the agent must infer that mapping.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.