get_matches_by_date查询某一天的全部赛程与比分，覆盖足球、篮球、网球、棒球等项目的全部联赛与杯赛。用户问「今天有什么比赛」「昨天的赛果」「周末的赛程」时用这个工具。date 省略时返回今天（东八区）的赛程，可查询范围为往前 365 天至往后 7 天。只想知道此刻正在踢的比赛，请改用 get_live_matches。
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | 日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-09。省略则取今天。 |
Changes observed during successful MCP inspections.
Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-06。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-09。省略则取今天。"Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-05。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-06。省略则取今天。"Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-02。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-05。省略则取今天。"Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-01。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-02。省略则取今天。"Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-09-30。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-10-01。省略则取今天。"Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-09-29。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-09-30。省略则取今天。"Input schema / properties / date / descriptionPrevious value: -"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-09-28。省略则取今天。"New value: +"日期，格式 YYYY-MM-DD（东八区自然日），例如 2026-09-29。省略则取今天。"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds substantive behavior the annotations do not: omitted date defaults to today in UTC+8, and the queryable window is -365 to +7 days, which is a real constraint an agent must respect. It doesn't discuss result volume or pagination behavior, but that is minor for a read-only lookup.
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 sentences, front-loaded with what the tool returns, then when to use it, then the exclusion routing to get_live_matches. Every sentence carries distinct information and none is 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?
No output schema exists, but the description defines the returned scope (all leagues/cups across multiple sports for one day) with enough precision. Combined with the range and default-date behavior, an agent has everything needed to invoke it 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 description coverage is 100% and the schema already documents the YYYY-MM-DD format, the UTC+8 natural-day semantics, and the default-to-today behavior. The description's added value is the queryable range (前 365 天至后 7 天), which the schema does not state and which materially affects valid inputs.
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 specific verb+resource (查询某一天的全部赛程与比分) plus the scope of coverage (足球、篮球、网球、棒球等项目的全部联赛与杯赛). It also differentiates from the sibling get_live_matches, which it names explicitly. An agent can select it 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?
It gives concrete trigger utterances (「今天有什么比赛」「昨天的赛果」「周末的赛程」) and an explicit exclusion with the alternative: for in-progress matches use get_live_matches. It also states the default when date is omitted, so the call path is fully determined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.