Skip to main content
Glama

Search official Roblox documentation

search_creator_docs
Read-only

Find and read pages from Roblox's official creator documentation (create.roblox.com/docs). Call with query to list matching pages, then call again with path from a result to read that page in full.

Instructions

Find and read pages from Roblox's official creator documentation (create.roblox.com/docs). Call with query to list matching pages, then call again with path from a result to read that page in full. Use this for intended behaviour, limits and quotas, and guide-level explanations — pair it with search_devforum for what actually happens in production.

Input Schema

NameRequiredDescriptionDefault
pathNoRepo path from a previous result, e.g. content/en-us/cloud-services/data-stores/index.md, or a create.roblox.com/docs URL. Returns the full page.
limitNo
queryNoWhat to look for, e.g. "data store limits" or "ProximityPrompt".
max_tokensNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.3.4
    • changedInput schema / properties / path / description
      Previous value: -"Repo path from a previous result, e.g. content/en-us/cloud-services/data-stores/index.md. Returns the full page."New value: +"Repo path from a previous result, e.g. content/en-us/cloud-services/data-stores/index.md, or a create.roblox.com/docs URL. Returns the full page."
  2. First observedv1.0.2

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already establish readOnly/openWorld/non-destructive, so the lower bar applies; the description still adds value by disclosing that one call lists matches and a second reads a full page, which the annotations cannot convey. It stops short of describing pagination, ranking of query results, or truncation behaviour when a page exceeds max_tokens.

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?

Two sentences, front-loaded with the resource and the call pattern, with zero filler. The query-then-path sequence appears before the softer usage commentary, so the actionable part is read first.

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 4-param read tool with no output schema, the description covers what the tool returns at a conceptual level (list of matches, then full page) and how it relates to siblings. The remaining hole is token-budget behaviour and whether query and path can be combined in one call.

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 50%: query and path are documented in the schema, and the description usefully clarifies that path must come from a prior result. However, it says nothing about limit or max_tokens, and max_tokens (default 3000, cap 12000) directly determines whether a long page comes back truncated — a material gap for a read tool.

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 concrete verb and resource ("find and read pages from Roblox's official creator documentation") and names the exact domain (create.roblox.com/docs). It also distinguishes itself from sibling search_devforum by framing itself as the source for intended behaviour vs. production reality.

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 describes the two-step workflow: query first to list matching pages, then path from a result to read the full page. It also names the topical cases (limits, quotas, guide-level explanations) and prescribes pairing with search_devforum, which is the exact alternative an agent would otherwise confuse it with.

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