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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the response varies depending on whether an API key is present, and the request-usage window is fixed at 7 days. It stops short of stating error behavior for invalid/expired keys.

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?

A single sentence that front-loads the primary distinction (live vs demo data) and then appends the keyed-detail fields. It is efficient with no filler, though the trailing list of six returned fields makes the sentence dense and slightly harder 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?

With zero parameters, a 100% covered schema, and no output schema (so return-shape explanation is not required), the description supplies what an agent needs: what the tool reports and the conditional keyed behavior. Minor gap in not clarifying what is returned when no API key is supplied.

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?

The tool takes zero parameters and schema coverage is 100%, so the baseline is 4. The mention of 'with an API key' describes an ambient credential rather than a schema parameter, and no parameter-level semantics are needed. There is minor ambiguity because the description implies an input (the key) that does not appear in 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 uses a specific verb ('Show') and names the exact resource: server data mode (live vs demo) plus API-key status fields. This is immediately distinguishable from all siblings, which deal with sports, matches, and tournaments rather than account/server state. It lacks only an explicit framing sentence stating the tool's overall role.

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 this is the tool to check authentication/account state, and the phrase 'with an API key' hints at a keyed vs unkeyed branch. However, there is no explicit when-to-use guidance, no prerequisites (e.g., how the key is supplied), and no statement of when this tool should be preferred over any sibling.

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 cover the safety profile (readOnly, idempotent, openWorld). The description adds real behavioral context beyond them: odds are decimal, 'blocked' means a suspended selection, a match can have hundreds of markets, and sub-events must be fetched via a recursive call with the same line_type.

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 return-contents sentence, then two tight sentences on filtering and sub-event recursion. Dense but no filler; slightly list-like in the first line.

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 burden of describing returns and does so well (score, stats, markets, odds, sub-events). It doesn't address scale/pagination behavior for the default market set, but the schema's max_markets and default annotations fill most of that gap.

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 baseline is 3. The description goes further by illustrating the `markets` filter with concrete values (["1X2", "Total"]) and by explaining that line_type is what ties a sub-event's game_id back to a valid get_match call, linking two parameters semantically.

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 ('Full details of one match') and enumerates the payload: score, live statistics, markets, odds, sub-events. That clearly distinguishes it from the list_*/search_matches siblings, which return sets of matches rather than one match's detail.

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 useful operational guidance — filter with `markets`, and re-call get_match with a sub-event's own game_id plus the same line_type to drill down. However it never states when to prefer this over alternatives (search_matches, list_live_matches) or any precondition, so the usage guidance 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 readOnlyHint/idempotentHint/openWorldHint, so safety is covered. The description adds real behavioral value beyond that: it describes the shape of the returned hierarchy and the match counts per level. It omits any note on caching, freshness, or rate limits for a live-data endpoint.

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 short sentences, front-loaded with what the tool returns, then the two mode-specific behaviors. No filler and every clause 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 carries the burden of describing the return structure and does so (sports with match counts, countries, tournaments with ids). Combined with full schema coverage for the three parameters, 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 all three parameters (esports, sport_id, line_type) are already documented including the enum values. The description restates the sport_id branching behavior but adds little syntax or format detail 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 concrete verb+resource ('navigation tree sport -> country -> tournament') and immediately scopes it by line type. The two-mode behavior (whole tree vs. one sport's subtree) makes it clearly distinguishable from sibling flat listers like list_sports, list_countries and list_tournaments.

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 a concrete downstream use case: use the returned tournament_id for list_live_matches / list_prematch_matches, and explains the with/without sport_id selection condition. It does not, however, explicitly say when to prefer this over list_tournaments or list_countries, which overlap in scope.

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, idempotentHint and openWorldHint, so the safety profile is covered. The description adds a genuine behavioral detail beyond the annotations: only countries/regions that actually have matches are returned, and counts accompany them, which tells the agent the result set is pre-filtered rather than a full country list.

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?

A single sentence with the resource front-loaded and no filler. Every clause (scope = one sport, filter = has matches, payload = match counts) 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?

For a read-only, two-parameter listing tool with no output schema, the description plus the fully documented schema cover what is needed to call it. It does not clarify how line_type affects the counts or the ordering of results, which is a minor gap.

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 sport_id and line_type (including the live/prematch enum) are fully documented in the schema. The description only restates the 'one sport' scoping and adds no format or lookup detail, 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?

The description states a clear verb and resource ('List the countries (regions)') plus the scoping filter ('that have matches in one sport') and the return content ('with match counts'). It is readily distinguishable from siblings like list_tournaments or list_live_matches by resource, though no sibling is named explicitly.

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 by 'in one sport, with match counts' — an agent can infer this is the country-breakdown step after picking a sport. However, there is no explicit when-to-use, no when-not-to-use, and no mention of alternatives such as list_tournaments for a different grouping.

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, idempotentHint and openWorldHint, so the safety profile is covered. The description adds that results are grouped by tournament and that ids feed get_match with line_type 'live', but says nothing about result size, pagination, or freshness/latency of live data.

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 sentences, front-loaded with the resource and its payload, followed by the precise next-step tool. No filler and nothing redundant.

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 names what is returned (score, period, minute, main odds, tournament grouping), which is exactly what an agent needs to decide to call it. It leaves minor gaps around response size and the overview-vs-filtered mode that the schema covers, so not quite 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 description coverage is 100% and every parameter (limit, esports, markets, sport_id, include_odds, tournament_id, max_markets_per_match) is documented in the schema itself. The description only alludes to default markets and does not add syntax or interaction details beyond 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 and resource ('list_live_matches' → live in-play matches) and enumerates the returned fields (score, period, minute, main odds) plus grouping by tournament. The 'Live (in-play)' qualifier implicitly distinguishes it from the sibling list_prematch_matches, though 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?

Explicitly routes the agent onward: use get_match with a game_id from here (line_type 'live') for all markets and live stats. This gives clear context for the tool's role as an overview entry point. It does not state when not to use it versus list_prematch_matches or top_matches, so it stops short of full when/when-not guidance.

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/openWorld/idempotent, so the safety profile is covered. The description adds real behavioral context the annotations don't: the default 'Top' selection of 50 matches, the top-leagues-then-start-time ordering, and the full_line/tournament_id interaction. Return-format and paging details are absent, keeping it from a 5.

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, front-loaded with the resource and its shape, then default-behavior caveats, then the get_match handoff. Every sentence carries non-redundant 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?

For a 10-parameter read tool with no output schema, the description covers the essential behavior (default selection size, ordering, day/within_hours scheduling, drill-down path). It is adequately complete, with only minor gaps around return shape that do not block 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 coverage is 100% so the baseline is 3, but the description adds genuine semantics on top: what tournament_id 0 means (whole-sport 'Top' selection of 50) and how full_line changes it. It doesn't explain the markets/limit/esports parameters, but it enriches the two most consequential ones.

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 with scope: upcoming prematch matches, start time, main odds, grouped by tournament. The '(Prematch)' qualifier implicitly separates it from list_live_matches, but it never names siblings or contrasts itself with top_matches/search_matches, so a 4 rather than 5.

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 routing: use within_hours or day for a schedule, and use get_match with a game_id from the results (line_type 'prematch') for all markets. That is clear when-to-use guidance and a named handoff tool, though it doesn't state when NOT to use this tool versus top_matches.

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/idempotentHint/openWorldHint, so the safety profile is covered. The description adds real behavior ('Sports without matches are not listed', match counts in the result), but it is muddled as to whether both Live and Prematch are returned or only the line_type selected, which the enum/default implies is a single value.

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 sentences, zero filler, with the scoping constraint and the 'start here' guidance both front-loaded. Every clause 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?

There is no output schema, so the description sensibly names what comes back (sport_id, match counts). It is nearly sufficient for a two-parameter read-only discovery tool, with only the live-vs-prematch coverage ambiguity left unresolved.

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 the esports and line_type parameters are already fully documented with enums and defaults; baseline 3 applies. The description only echoes the live/prematch notion and never mentions esports mode, adding no meaning 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?

States a specific verb and resource ('List the sports') scoped to 'Live or Prematch matches right now, with match counts', which is far more precise than the bare tool name. The sentence 'Start here to get a sport_id' positions it in the workflow relative to siblings like list_tournaments and get_match.

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?

Explicitly frames the tool as the entry point ('Start here to get a sport_id'), which tells the agent when to reach for it before deeper match tools. It does not name a competing sibling or state a when-not condition, so it stops short of full routing guidance.

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, idempotentHint and openWorldHint, so the safety profile is covered. The description does add one meaningful behavioral detail beyond them: results are restricted to tournaments that actually have matches and each carries match counts. It says nothing about ordering, pagination, or whether an empty list is possible.

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?

A single front-loaded sentence that names the resource, the filters, and the returned data with zero filler.

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 necessary work of indicating the return content (match counts) and the filtering behavior. Gaps remain around result ordering/paging and the tournament-vs-championship distinction, but for a simple read-only list tool it is largely sufficient.

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 all four parameters (esports, sport_id, line_type, country_id) are already documented with defaults, enums, and ID provenance in the schema. The description only alludes to sport/country scoping and adds no syntax or format meaning beyond it.

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 ('List the tournaments') plus scoping conditions (one sport and country, only those with matches) and the payload ('with match counts'). However, it never distinguishes itself from the closest sibling, top_championships, so an agent must infer the difference between tournaments and championships.

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 gives no when-to-use guidance, no prerequisites (that sport_id/country_id must first be resolved via list_sports/list_countries), and no indication of when top_championships or the match-listing tools are preferable.

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?

With readOnlyHint, openWorldHint and idempotentHint already declared, the description adds genuine context by enumerating the returned fields (game_id, teams, tournament, start time, Live score) and signalling what is absent (odds, deferred to get_match). It does not cover result ordering, truncation, or the effect of the default limit.

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, zero filler. The search scope is front-loaded and the return-field summary plus the get_match hand-off come second, which is the right order.

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, describing the returned fields is essential and it does so. The search surface is left partly implicit but is recoverable from line_type in the schema; only pagination/limit behaviour and result ordering remain unaddressed for a 3-param tool.

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 text, limit, and line_type are already documented with examples, bounds, and an enum. The description only restates that matching is by team/participant name, adding no syntax or matching-rule detail 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 (find), resource (matches) and the search key (team or participant name), then names the sibling it is not (get_match) and why. An agent can distinguish it from list_live_matches, top_matches, and get_match without opening any 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?

It gives a clear use context (lookup by team/participant name) and explicitly routes odds lookups to get_match, which is the key alternative. It stops short of stating when not to use it (e.g., browsing by tournament or country, which other siblings cover), so no full when/when-not pairing.

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 cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), so the bar is low. The description still adds real behavioral content the annotations lack: a hard cap of 12 results and the deliberate exclusion of esports, both of which affect interpretation of the output.

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, the result shape and scope constraints front-loaded, and the follow-up instruction second. 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?

There is no output schema, and the description compensates by naming the returned fields (championships plus match counts), the result cap, and the esports exclusion, plus how to use the returned id. Only the ranking criterion for 'popular' is left unstated.

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?

The single line_type parameter has 100% schema coverage with an enum and a description of both values, so the schema carries the meaning. The description only gestures at the live/prematch split indirectly by naming the two match-listing siblings; it adds no syntax or default guidance 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?

States the resource (popular championships/tournaments) and the payload (match counts, capped at 12, esports excluded). It implicitly separates itself from list_tournaments via 'popular'/'without esports', though that contrast is never made explicit.

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 downstream routing: take the tournament_id from here and feed it to list_live_matches or list_prematch_matches. It stops short of stating when to prefer this over list_tournaments or top_matches, so it is clear context without exclusions.

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, openWorld and idempotent, so safety is covered. The description contributes the hard cap of 10 results and the Prematch-only caveat for sport scoping, which is genuine added context, but says nothing about ordering/freshness or how 'popular' is determined beyond the '(API order)' hint in the 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?

Two short sentences, zero waste, with the 10-match popularity scope front-loaded before the use-case gloss. Nothing redundant 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?

For an all-optional, four-parameter read tool with full schema coverage, annotations and no output schema, the description covers the essentials plus the result cap. It slightly under-serves by not clarifying ranking/freshness semantics or the live-vs-prematch differentiation that line_type exposes.

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 schema already documents sport_id, line_type, include_odds and max_markets_per_match. The description only restates the sport_id Prematch-only restriction, adding no new parameter meaning beyond the structured fields; 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?

The description names a concrete resource and quantifies scope: 'up to 10 most popular matches right now.' It is clearly a curated popularity-ranked list, distinct from list_live_matches/list_prematch_matches, but it never names those siblings to sharpen 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?

The framing 'a quick answer to "what are the big games?"' implies the discovery/browse use case, which is helpful implied guidance. However it gives no explicit when-to-use-vs-alternatives routing, e.g. why to pick this over list_live_matches or search_matches.

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