Skip to main content
Glama

Rokha

by ai.rokha
OverviewDiscussionsAdmin

Search the Rokha Registry

registry_search
Read-only

Search EVERY major skill/MCP registry at once (clawhub, Glama, the official MCP registry, Smithery, skills.sh, Docker MCP, Anthropic and more — the live count is in GET /api/marketplace/registry/stats) by free-text query. Returns name, slug, provider, author, version, downloads, and description for each match. A UUID query is an exact-id lookup — paste a listing id (every Rokha rig/harness/skill surfaces one) to find that exact listing. Follow up with registry_get_skill to fetch a skill's full SKILL.md and install metadata. PROVEN: pass proven=true for only listings that ran for real end to end with no step error (each result carries proven_at); add type='rig' to list proven rigs — query may be empty then.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoOnly this listing type, e.g. 'rig'
limitNoMax results (default 10, max 25)
queryNoFree-text search, e.g. 'UI design' or 'summarize youtube'
provenNotrue = only PROVEN listings (ran for real to a result, no step error)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / proven
      Added value: +{
+  "description": "true = only PROVEN listings (ran for real to a result, no step error)",
+  "type": "boolean"
+}
    • addedInput schema / properties / type
      Added value: +{
+  "description": "Only this listing type, e.g. 'rig'",
+  "enum": [
+    "rig",
+    "skill",
+    "mcp",
+    "harness"
+  ],
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "query"
-]
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint/destructiveHint, so the description carries the behavioral load — and it does deliver: the returned field set (name, slug, provider, author, version, downloads, description), the meaning of a UUID query as exact-id lookup, and the proven_at semantics of the proven flag. It omits pagination/rate-limit behavior, keeping it below the top of the scale.

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?

Purpose and scope are front-loaded and the text is dense with operational detail rather than filler, but the embossed 'EVERY'/'PROVEN:' caps and the inline 'GET /api/marketplace/registry/stats' path add noise that does not help the agent decide or call the tool.

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 no output schema and no nesting, the description compensates by listing the returned fields, describing the id-lookup mode, and pointing to registry_get_skill for detail retrieval. Nothing material an agent needs to search correctly or interpret results 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% (baseline 3), and the description adds real meaning beyond the schema: a UUID-looking query switches to exact-id lookup, query may be empty when type='rig' with proven=true, and proven maps to the proven_at field per result. This is genuine clarification of parameter interaction rather than restatement.

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 (search) plus an explicit multi-registry scope and enumerates the sources (clawhub, Glama, official MCP registry, Smithery, etc.), and describes the id-lookup mode, so it is clearly distinguishable from rig_search/search_skills/search_harnesses siblings. An agent can tell what it does without opening the schema.

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?

Gives concrete usage conditions: pass proven=true for verified listings, add type='rig' (query may then be empty) to list proven rigs, and follow up with registry_get_skill for full SKILL.md and install metadata — a named alternate tool for the next step. It does not explicitly say when NOT to use it versus rig_search or search_skills, so it stops short of a full routing rule.

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

All Rokha toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources