gpuclouds

search_listings

Read-onlyIdempotent

Search published GPU cloud providers by text, place and category.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

Name	Required	Description
`q`	No	Search text, with at least one letter or digit. Matches name, categories, attributes, description and place. Typos fall back to close matches.
`city`	No	City slug, from /places.
`sort`	No	`relevance` needs `q` and is the default with it. `name` is the default without `q`. `recent` is newest first.
`limit`	No	Items per page.
`cursor`	No	`page.nextCursor` from the previous response. Opaque. Send the same filters and `limit`.
`region`	No	Region slug, from /places.
`country`	No	ISO 3166-1 alpha-2 country code, any case. A country the directory does not cover, as listed in /places, gives 400.
`category`	No	Category slug, from /categories. A parent slug also matches its children.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare this is a read-only, idempotent, non-destructive search, so the safety profile is covered. The description adds only the 'published' scope, and it says nothing about pagination or ranking behavior beyond what the cursor and sort schema entries imply.

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?

One front-loaded sentence with no filler. It is efficient but arguably too terse for an 8-parameter search tool, leaving structural gaps rather than excess.

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

Completeness3/5

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

The tool has 8 optional parameters, cursor pagination, and no output schema, so the description carries a heavy burden that it only partly meets: 'published' is not defined, and there is no hint that filtering is combined across q, place, and category, or that slugs must come from /places and /categories.

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 each of the 8 parameters is already documented in the schema, including sort defaults and the cursor round-trip rule. The description adds no further parameter meaning, so the baseline of 3 is correct.

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 has a specific verb (search) and resource (published GPU cloud providers) and outlines its searchable facets: text, place and category. It does not name a sibling, so an agent must infer the difference from get_listing and list_places.

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

Usage Guidelines2/5

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

Nothing states when to use this search instead of get_listing or list_places. The word 'published' hints at a scope restriction, but no explicit 'use this when…' guidance or exclusions are given.

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

All gpuclouds 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?