Skip to main content
Glama
bili-material-mcp
by sac432

search_videos

Read-onlyIdempotent

Search Bilibili videos by keyword and return compact results with title, uploader, engagement counts, duration, and publish date. Sort by relevance, views, date, danmaku, favorites, or comments.

Instructions

Search Bilibili videos. Returns one line per video: bvid | title | uploader | play/like/comment counts | duration | publish date. limit is capped at 20. order: totalrank (default), click, pubdate, dm (danmaku), stow (favorites), scores (comments).

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": {
      "keyword": "<keyword>"
    },
    "name": "search_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
orderNototalrank
keywordYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is largely covered, yet the description still adds non-obvious operational facts: results are one line per video with a fixed field layout, and limit is hard-capped at 20 regardless of what the caller requests. Those are real constraints an agent cannot get from the annotations.

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

Conciseness5/5

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

Four compact sentences: purpose first, then return shape, then the hard limit, then the ordering options. Every clause carries distinct information with no repetition of the schema or title.

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?

For a 3-parameter search tool with no output schema, the description supplies return-row structure, a hard limit, and full enum semantics, which is most of what an agent needs. Remaining gaps are pagination (there appears to be none) and keyword matching scope.

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 0%, so the description has to carry parameter meaning, and it does substantially: it decodes the cryptic order enum values (dm = danmaku, stow = favorites, scores = comments) and warns about the limit cap. Keyword is left at face value with no note on what is matched (title, tags, uploader), which keeps it short of a 5.

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?

States a specific verb and resource ("Search Bilibili videos") and immediately shows what comes back, which cleanly separates it from the sibling get_* retrieval tools. An agent can tell from the first clause that this is a keyword-driven discovery tool, not a lookup by ID.

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 word "Search" and the required keyword, but there is no explicit statement of when to prefer this over the digest/comment/subtitle siblings, and no note on when a query would be better served elsewhere. Adequate for a self-evident search tool, but guidance is inferred rather than stated.

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