Skip to main content
Glama

Boxerbook

Boxing results

boxing_results
Read-onlyIdempotent

Completed professional bouts of the last N days (N calendar days ending today: 1 = today, 2 = last night and today, up to 14), newest first: winner, method, round, time, both records going in, the sources of each result and the boxerbook.com url of each bout. Answers "who won last night", "results this weekend" and "did A beat B", asked in any language. At most 60 bouts per answer, whole days first: a longer window comes back truncated with next_arguments (before_date) for the older days. Pass lang matching the user's language (en, es, ru or ja) so the page links match it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "boxing_results"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNonumber of days ending today (default 2: last night and today)
langNothe user's language: en (default), es, ru or ja; the boxerbook.com page links of the answer follow it (a page without a translation keeps its English link)en
skipNobouts of the first day to pass over: set by next_arguments when one day is longer than a page
countryNoISO 3166-1 alpha-2 country of the bout, e.g. GB, US, MX
divisionNodivision code (hea, wel, w_fea) or name (heavyweight, women's featherweight)
before_dateNokeep only the bouts before this date (YYYY-MM-DD, UTC): the next page of a truncated answer

Output Schema

NameRequiredDescriptionDefault
toNo
urlNo
citeYesthe markdown link to quote with any fact of this answer: Source: [Boxerbook](<url of the main page>)
daysNo
fromNo
moreNowhat the cap left out and how to ask for it
as_ofYes
boutsYes
countryNo
partialNotrue when part of the data could not be read this time; retry in a minute for the full answer
divisionNo
truncatedNotrue when the 400-bout cap of the underlying list may have dropped bouts of this window (narrow it with days, country or division)
attributionYes
shown_boutsNobouts in this answer
total_boutsNobouts in the asked window
next_argumentsNothe arguments of the call that returns the next page

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / attribution / properties / license / const
      Previous value: -"ODbL"New value: +"Boxerbook data terms"
    • addedOutput schema / properties / attribution / properties / terms
      Added value: +{
      +  "format": "uri",
      +  "type": "string"
      +}
  2. Changed11 schema fields changed
    • addedInput schema / properties / before_date
      Added value: +{
      +  "description": "keep only the bouts before this date (YYYY-MM-DD, UTC): the next page of a truncated answer",
      +  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +  "type": "string"
      +}
    • addedInput schema / properties / lang
      Added value: +{
      +  "default": "en",
      +  "description": "the user's language: en (default), es, ru or ja; the boxerbook.com page links of the answer follow it (a page without a translation keeps its English link)",
      +  "enum": [
      +    "en",
      +    "es",
      +    "ru",
      +    "ja"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / skip
      Added value: +{
      +  "description": "bouts of the first day to pass over: set by next_arguments when one day is longer than a page",
      +  "maximum": 2000,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / bouts / items / properties / display
      Added value: +{
      +  "description": "the order to show the two names in: ['a','b'] or ['b','a'] (the better-known boxer first, as boxerbook.com does: more Wikipedia language links, then the Boxerbook rating, then pro bouts). a, b, winner, forecast.p_a and market.p_a keep their meaning (side a); only the display order changes",
      +  "items": {
      +    "enum": [
      +      "a",
      +      "b"
      +    ]
      +  },
      +  "maxItems": 2,
      +  "minItems": 2,
      +  "type": "array"
      +}
    • changedOutput schema / properties / bouts / items / required
      Previous value: -[
      -  "id",
      -  "date",
      -  "a",
      -  "b",
      -  "winner",
      -  "sources"
      -]New value: +[
      +  "id",
      +  "date",
      +  "a",
      +  "b",
      +  "display",
      +  "winner",
      +  "sources"
      +]
    • addedOutput schema / properties / cite
      Added value: +{
      +  "description": "the markdown link to quote with any fact of this answer: Source: [Boxerbook](<url of the main page>)",
      +  "type": "string"
      +}
    • addedOutput schema / properties / more
      Added value: +{
      +  "description": "what the cap left out and how to ask for it",
      +  "type": "string"
      +}
    • addedOutput schema / properties / next_arguments
      Added value: +{
      +  "description": "the arguments of the call that returns the next page",
      +  "type": "object"
      +}
    • addedOutput schema / properties / shown_bouts
      Added value: +{
      +  "description": "bouts in this answer",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / total_bouts
      Added value: +{
      +  "description": "bouts in the asked window",
      +  "type": "integer"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "bouts",
      -  "attribution",
      -  "as_of"
      -]New value: +[
      +  "cite",
      +  "bouts",
      +  "attribution",
      +  "as_of"
      +]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real operational detail on top: a hard cap of 60 bouts per answer, whole-days-first ordering, and the truncation contract where a longer window returns next_arguments (before_date) for older days. It also discloses that lang changes the page links, which is a side effect the agent must know to explain output differences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded — scope, return fields, then limits and pagination — and every clause carries information. The first sentence is an overlong run-on that could be split, and the question examples sit slightly awkwardly after the field enumeration, but there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema handling return shapes and annotations covering safety, the description supplies exactly what remains: the time-window definition, the 60-bout cap, and how to continue past a truncation. Nothing needed to invoke it correctly or interpret a truncated response is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 goes further: it spells out the days semantics (1 = today, 2 = last night and today, ceiling of 14) and the purpose of lang (matching page links to the user's language) in terms an agent can act on. The skip and before_date pagination parameters are linked to the truncation behavior, though their individual meaning is largely left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Completed professional bouts of the last N days" names a specific verb (list completed bouts), the resource (bouts), the time scope, and enumerates the returned fields (winner, method, round, time, records, sources, url). The word "completed" separates it from schedule-style siblings such as boxing_schedule or next_fight without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete query phrasings it answers ("who won last night", "results this weekend", "did A beat B"), which tells the agent when to reach for it. It stops short of naming an alternative sibling for the forward-looking or per-boxer cases, so no explicit exclusion is offered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.