Skip to main content
Glama

Boxerbook

Fetch a Boxerbook document

fetch
Read-onlyIdempotent

The full document for a Boxerbook document id: a boxer card, a bout (records, result, broadcasters, forecast, market, sources), a card with its bouts, or a division's rankings, as Markdown text with metadata. An unknown id returns an error. Pass lang matching the user's language (en, es, ru or ja) so the page links match it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

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

Input Schema

NameRequiredDescriptionDefault
idYesa document id: boxer:<id>, bout:<id>, event:<id> or rankings:<DIV>
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

Output Schema

NameRequiredDescriptionDefault
idYes
urlYes
textYesthe document as Markdown; its last line is the markdown link of its boxerbook.com page
titleYes
metadataYestype and ids of the document, plus source, license, attribution_url, as_of (and partial when part of the data could not be read)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / id / description
      Previous value: -"an id from search: boxer:<id>, bout:<id>, event:<id> or rankings:<DIV>"New value: +"a document id: boxer:<id>, bout:<id>, event:<id> or rankings:<DIV>"
    • 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"
      +}
    • addedOutput schema / additionalProperties
      Added value: +false
    • removedOutput schema / properties / as_of
      Removed value: -{
      -  "description": "ISO UTC time of this answer",
      -  "type": "string"
      -}
    • removedOutput schema / properties / attribution
      Removed value: -{
      -  "properties": {
      -    "license": {
      -      "const": "ODbL"
      -    },
      -    "source": {
      -      "const": "Boxerbook"
      -    },
      -    "url": {
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "source",
      -    "license",
      -    "url"
      -  ],
      -  "type": "object"
      -}
    • addedOutput schema / properties / metadata / description
      Added value: +"type and ids of the document, plus source, license, attribution_url, as_of (and partial when part of the data could not be read)"
    • removedOutput schema / properties / partial
      Removed value: -{
      -  "description": "true when part of the data could not be read this time; retry in a minute for the full answer",
      -  "type": "boolean"
      -}
    • changedOutput schema / properties / text / description
      Previous value: -"the document as Markdown"New value: +"the document as Markdown; its last line is the markdown link of its boxerbook.com page"
    • addedOutput schema / properties / url / minLength
      Added value: +1
    • changedOutput schema / required
      Previous value: -[
      -  "id",
      -  "title",
      -  "text",
      -  "url",
      -  "metadata",
      -  "attribution",
      -  "as_of"
      -]New value: +[
      +  "id",
      +  "title",
      +  "text",
      +  "url",
      +  "metadata"
      +]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: an unknown id returns an error, and the payload is Markdown text with metadata rather than JSON — useful for an agent composing an answer. No mention of size limits or truncation for large documents.

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?

Three tightly packed sentences with the payload description front-loaded, then the failure mode, then the locale rule — every sentence earns its place. The nested parenthetical listing bout fields is dense but scannable and adds real information.

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

Completeness4/5

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

With an output schema present, return-value detail is optional, yet the description still characterizes the output as Markdown with metadata. Combined with the error behavior and locale rule, an agent has nearly everything needed; only document-size/pagination behavior is unaddressed.

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

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents both the id formats and the lang enum with its default and link behavior. The description's lang sentence largely restates the schema, adding only the framing 'matching the user's language'. Baseline 3 applies when the schema carries the parameter semantics.

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

Purpose4/5

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

The description states a specific resource and scope: 'The full document for a Boxerbook document id', then enumerates the document kinds (boxer card, bout, card with bouts, division rankings) with the fields a bout record carries. This lets an agent distinguish the full-document fetch from summary-oriented siblings like search or boxing_results, though it never names a sibling explicitly.

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

Usage Guidelines3/5

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

Usage is implied by the document-type enumeration and the error note for unknown ids, and the lang instruction gives a concrete calling rule. But there is no explicit when-to-use-this-vs-siblings guidance (e.g., fetch vs bout vs boxer vs rankings), which is a real gap given ten sibling tools covering overlapping data.

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.