TuLotero

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. The description adds meaningful context beyond that: the content is sourced from SELAE regulations and no account is needed. It stops short of describing output format or length, which is acceptable given the low-risk read nature.

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 the purpose, then examples, exclusions and the supported-game list — every sentence carries information. It is fairly dense but not padded, and the game enumeration, while long, is necessary given there is no enum in the schema.

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 does the work of describing what the caller receives (rules, price, calendar, prize categories, payout). The only gap is the unresolved probability contradiction and no guidance on answer length, but for an informational read-only tool it is otherwise complete.

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 'tema' and 'juego' are already documented, establishing the baseline of 3. The description reinforces the answer facets (precio, calendario, premios, cobro) that map to 'tema', but it also says probabilities are NOT included while the schema lists 'probabilidad' as a valid 'tema' value — a mild inconsistency that undermines rather than helps parameter understanding.

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: 'Reglas oficiales de un juego, con la normativa de SELAE citada', and enumerates exactly what the answer covers (qué se juega, cuánto cuesta, cuándo se sortea, premios, cobro). This clearly separates it from siblings like resultado_sorteo (results) and comprobar_premio (prize checking).

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?

Provides concrete example questions and exclusions ('No incluye probabilidades ni recomienda números', 'No requiere tener cuenta'), giving strong context for when to reach for it. It does not name the sibling tools or spell out the fallback when a user actually wants results or a prize check, so routing is implied rather than explicit.

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 establish readOnly/openWorld safety. The description adds genuine context: no account required, and the behavior when a draw has no escrutinio yet (it says so along with the usual publication time). It also enumerates the returned prize breakdown, useful since there is no output schema.

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 action and value, then progressively adds examples, game list and edge-case behavior. It is long but nearly every sentence carries information; minor density loss from the clustered example questions.

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?

Covers the game whitelist, the two input families, the no-account fact, and the pending-escrutinio case, which is sufficient for a 7-parameter read-only tool whose return fields are listed in prose. Lacks only explicit sibling routing.

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 baseline is 3, but the description adds real mapping value: which parameter to populate per game family (decimos for Lotería Nacional/Navidad/El Niño, apuestas for number games) and that values read from a photo are accepted. That goes beyond the field-level schema text.

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 precise verb (comprueba) and resource (un décimo o una apuesta concreta) with scope: whether it has a prize and how much (bruto, retención, neto, categoría, plazo). The framing around the user's own play distinguishes it implicitly from siblings like resultado_sorteo, which only surface draw outcomes.

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 concrete trigger questions («tengo el 45433, ¿me ha tocado?») and per-game instructions (Lotería Nacional → decimos; juegos de números → apuestas), plus a note that photo-read numbers work. It never names an alternative or a when-not condition, so the routing against resultado_sorteo/sorteos is left to inference.

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 openWorldHint=true, so safety is covered. The description adds genuinely useful context beyond that: no account is required, results are published once TuLotero posts the escrutinio, and the response arrives as Markdown tables ready to display. It stops short of describing what happens when escrutinio is not yet available.

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?

One dense paragraph that is front-loaded with the purpose and payoff ('combinación ganadora... escrutinio con premios por categoría'), followed by example queries and the supported games. It is appropriately sized for a 12-game tool, though the game enumeration duplicates the enum-like list already in the schema and the comma-chained clauses are heavy to parse.

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 compensates by detailing the return content field-by-field (winning combination, jackpot status, reintegros, El Millón, category prizes, next draw) and its Markdown format. Combined with the auth-free note and the date default, an agent has everything needed to call and interpret 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?

Schema description coverage is 100%, so both parameters are already fully documented, including the free-form 'cuando' formats and the no-date default. The description reiterates the game list and the 'último celebrado' behavior without adding syntax or edge cases beyond the schema, so 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 ('el resultado de un sorteo ya celebrado') and then enumerates exactly what comes back: combinación ganadora, bote, reintegros, El Millón, escrutinio, Lotería Nacional, Quiniela, próximo sorteo. It also explicitly distinguishes itself from the sibling it is not: 'Si una jugada concreta tiene premio lo dice comprobar_premio'. An agent can route correctly without opening the 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?

Provides representative user phrasings ('resultado del Euromillones', '¿ha tocado el bote?') and names the alternative for per-bet checks (comprobar_premio), plus the key default ('Sin fecha devuelve el último celebrado'). It does not clarify the boundary with the sibling 'sorteos', even though it also surfaces next-draw info, so usage guidance is clear but not exhaustive.

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 openWorldHint=true, so safety is covered. The description adds genuinely useful behavior not in the annotations: no account required, no-argument default scope, and no number prediction.

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 purpose and example queries before the negative boundaries and the game list. The 12-game enumeration is long but earnable, since it defines the valid domain of the 'juego' parameter.

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, so the description takes on the burden and does state what comes back (jackpot, price, closing time), the default scope, and the exclusions. Minor gap: no mention of refresh cadence beyond 'al minuto' or any result-shape caveats, but nothing an agent needs to call it 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 coverage is 100%, so baseline is 3, but the description adds real operational meaning beyond the schema: with no arguments it returns today plus the coming days for all games, and the explicit instruction not to compute the date ('pásalo tal cual') is extra guidance the schema does not carry.

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 (upcoming draws with jackpot, price and closing time) and names the exact data domain (state lotteries in TuLotero). It also draws a clean boundary against the sibling resultado_sorteo by declaring it does NOT return already-held draws or predict numbers.

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 concrete user-question exemplars that map directly to the tool (jackpot amounts, weekend draws, is there a Bonoloto today, closing time for La Primitiva), plus the no-argument default. The explicit exclusion of past results routes the agent to resultado_sorteo when appropriate.

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