Skip to main content
Glama
Perplexity Web MCP

Perplexity Web MCP

by jacob-bd

pplx_gpt6_astra_thinking

GPT-6 Astra Thinking — OpenAI's most capable model with thinking. COSTS 1 PRO SEARCH QUERY. Requires Max subscription.

Instructions

GPT-6 Astra Thinking — OpenAI's most capable model with thinking. COSTS 1 PRO SEARCH QUERY. Requires Max subscription.

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_gpt6_astra_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

C2.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two valuable facts: the cost per call and the Max subscription requirement. Beyond that it is silent — no indication of whether the model browses the web by default, how conversation_id affects state, rate limits, or failure behavior. Partial disclosure, significant gaps.

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?

Two short sentences, front-loaded with the model identity and the cost warning, which is the operationally important part. 'Most capable model with thinking' leans on marketing language, but nothing is bloated.

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 described, but for a 3-parameter model-invocation tool with zero annotations the definition is thin. An agent still cannot tell what source_focus controls, whether conversation_id maintains context, or how this differs functionally from the many sibling model tools.

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

Parameters2/5

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

Schema description coverage is 0% across three parameters, so the description must compensate and does not. 'query' is self-evident from the name and required list, but source_focus (what sources, what values?) and conversation_id (thread continuity semantics) get no explanation whatsoever.

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

Purpose3/5

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

The description identifies the model (GPT-6 Astra Thinking) and characterizes it as 'most capable model with thinking', which lets an agent infer it answers queries via that model. However, it never states a verb or resource explicitly — no 'answers a query using...' — and the rest is branding plus cost. It only weakly distinguishes itself from the sibling pplx_gpt6_astra via the word 'thinking'.

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?

The only usage signal is 'COSTS 1 PRO SEARCH QUERY' and 'Requires Max subscription', which hints at expense but gives no when-to-use guidance. There is no comparison to cheaper/faster siblings like pplx_gpt6_astra or pplx_ask, and no exclusions or prerequisites beyond the subscription note.

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