Skip to main content
Glama
Perplexity Web MCP

Perplexity Web MCP

by jacob-bd

pplx_gemini4_hydrogen_thinking

Gemini 4 Hydrogen Thinking — Google's latest model with thinking. COSTS 1 PRO SEARCH QUERY.

Instructions

Gemini 4 Hydrogen Thinking — Google's latest model with thinking. COSTS 1 PRO SEARCH QUERY.

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": "pplx_gemini4_hydrogen_thinking"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
source_focusNoweb
conversation_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.17.0

TDQS

D1.8/5.0
Behavior1/5

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

No annotations exist, so the description carries the full behavioral burden. Its only behavioral claim is a cost of one pro search query; it says nothing about authentication, latency from 'thinking', rate limits, or whether conversation_id continues a prior thread — and it is silent on everything an agent needs to know before invoking a paid call.

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

Conciseness3/5

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

The text is short, front-loaded, and contains no filler, so there is nothing to trim. The problem is under-specification rather than verbosity: two fragments do not constitute an adequate definition for a three-parameter paid query tool.

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

Completeness2/5

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

An output schema exists, so return values need not be explained. However, with zero annotation coverage, zero schema description coverage, and a dense sibling set of interchangeable model names, the definition leaves the agent unable to distinguish invocation conditions or parameter formats.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters, including an untyped 'query', a 'source_focus' defaulting to 'web' with no enumerated values, and a nullable 'conversation_id'. The description explains none of them, so meaning must be guessed entirely from parameter names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name and adds only 'Google's latest model with thinking', which names a model rather than stating a specific action. It never says this tool sends a query to that model and returns an answer, nor how it differs from the many sibling model endpoints such as pplx_gemini4_carbon_thinking or pplx_gemini4_hydrogen.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named despite a large sibling family of near-identical model tools. The cost note hints at a trade-off but gives no rule for choosing this model over the cheaper or non-thinking variants.

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