Crawlora MCP

netshort_search

Read-only

Search NetShort's catalogue by keyword and return one page of matches with each result's shortPlayId, name, episode path, cover, synopsis, episode count and labels. This is the platform's only real search (its /search page ships just the site shell). The search is fuzzy rather than exact: an unmatched keyword still returns token matches, so treat results as approximate and never read an empty list as no such title, and dedupe by id when accumulating pages because page 2 can repeat ids from page 1. The upstream floors page 1 at 15 items, so a page can carry more than page_size. Take a result's id to netshort_title; language selects the locale (en_US or ja_JP) and results are locale-specific.

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": {
      "query": "<query>"
    },
    "name": "netshort_search"
  }
}

Input Schema

Name	Required	Description
`page`	No	1-based result page, default 1. Pages are not a strict partition: page 2 repeated 2 of page 1's 15 ids in the 2026-11-07 measurement, so dedupe by id when accumulating.
`query`	Yes	Required keyword. The search is fuzzy — an unmatched keyword still returns token matches, so treat results as approximate rather than exact matches.
`language`	No	Locale, one of: en_US (default), ja_JP. Results are locale-specific: the same keyword returns a disjoint catalogue per value. Only these two were measured; the site's other locale prefixes are not offered until they are.
`page_size`	No	Results per page, 1-50, default 10. The upstream applies a floor of 15 items on page 1, so a response can carry more items than requested.

Output Schema

Name	Required	Description	Default
`data`	Yes	The tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only supply readOnlyHint and openWorldHint, so the description carries the real burden and does: fuzzy token matching, non-partition pagination with concrete evidence (page 2 repeated 2 of page 1's 15 ids), the upstream 15-item floor, and locale-specific result sets. These are non-obvious traits an agent could not infer from the schema or annotations.

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?

Four sentences, front-loaded with purpose and return fields before the caveats. The dedupe and 15-item floor facts are repeated from the parameter schema, which is mild redundancy, but every sentence carries operational value and nothing is 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?

For a read-only fuzzy search with an output schema already defined, the description covers everything an agent needs: what comes back, how to interpret approximate matches, pagination quirks, locale scope and the natural next tool. No behavioral question relevant to correct invocation is left open.

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 description coverage is 100%, so page, query, language and page_size are already fully documented, and the description largely restates them (dedupe, 15-item floor, en_US/ja_JP locales). It adds the downstream pointer that a result's id feeds netshort_title, but that is workflow context rather than parameter meaning, so the baseline 3 applies.

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?

The first sentence gives a specific verb (search) and resource (NetShort's catalogue) plus the exact return shape: shortPlayId, name, episode path, cover, synopsis, episode count and labels. It further distinguishes itself from the browse/genres/title siblings by stating this is "the platform's only real search" and that its /search page ships only the site shell.

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

Usage Guidelines5/5

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

Explicitly routes the agent: use this to find titles by keyword, then take a result's id to netshort_title for detail. It also states the conditions that change interpretation of results (fuzzy matching, empty list is not proof of absence, dedupe across pages, page 1 floor of 15) and explains the locale tradeoff for the language parameter.

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

All Crawlora MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?