Skip to main content
Glama
Sign In
ProxyAPI-Perplexity

ProxyAPI-Perplexity

by spolperim-lab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Deep Research (Perplexity)

perplexity_research

Runs paid, multi-source deep research on a topic and returns a detailed cited report for large literature, market, or option-comparison reviews.

Instructions

Глубокое исследование темы через Perplexity Deep Research (perplexity/sonar-deep-research): десятки источников, развёрнутый отчёт со ссылками. Идёт от одной до нескольких минут и стоит ~15–70 ₽. Если не уложится в 60 с, вернёт job_id — тогда проверяй через perplexity_check, не запуская заново. Используй только для больших обзоров (литература, рынок, сравнение множества вариантов), для простых вопросов — perplexity_search. ВАЖНО: каждый вызов платный (списывается с баланса ProxyAPI пользователя). Перед вызовом обязательно спроси разрешение, показав вопрос, режим и примерную цену, и вызывай только после явного согласия. В конце ответа инструмент сам пишет фактическую стоимость — передай её пользователю.

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": "perplexity_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesТема исследования: что именно выяснить, для чего, какие аспекты важны
domainsNoИскать только на этих сайтах ["habr.com"] или исключить сайты через минус ["-pinterest.com"]. Не смешивать
recencyNoТолько свежие источники: за последний час/день/неделю/месяц/год
academicNoИскать по научным публикациям (с ним фильтры по датам не работают)
languagesNoЯзыки источников, коды ISO 639-1: ["ru", "en"]
after_dateNoТолько опубликованное после даты, формат ММ/ДД/ГГГГ
max_tokensNoЛимит длины ответа (по умолчанию зависит от режима)
before_dateNoТолько опубликованное до даты, формат ММ/ДД/ГГГГ

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description adds far more: runtime of one to several minutes, cost of ~15–70 ₽ charged to the user's ProxyAPI balance, a 60-second timeout that returns a job_id, and the fact that the tool appends actual cost to its response. This is exactly the kind of context annotations cannot carry.

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?

Front-loaded with what the tool is and its cost/time profile, then usage routing, then the mandatory permission rule. Dense but nearly every clause carries operational value; the cost point is stated twice (approximate price up front, actual cost at the end), which is slightly redundant but defensible.

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?

For an 8-parameter, expensive, potentially long-running tool with no output schema, the description covers cost, latency, timeout/async fallback, billing source, and the consent requirement. Nothing an agent needs to call it safely and correctly is missing.

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 every parameter is already documented in the schema, and the description adds no syntax or format detail beyond it. Baseline 3 applies. Minor note: the description mentions showing 'режим' (mode) in the permission prompt, but no mode parameter exists in the schema, which is a small mismatch rather than a contradiction.

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 and resource ('Глубокое исследование темы через Perplexity Deep Research'), names the underlying model, and explicitly distinguishes itself from perplexity_search for simple questions and perplexity_check for job polling. An agent can route correctly without opening any schema.

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?

Gives explicit when-to-use ('только для больших обзоров: литература, рынок, сравнение множества вариантов'), when-not ('для простых вопросов — perplexity_search'), and the async follow-up path ('проверяй через perplexity_check, не запуская заново'). It also mandates a permission step before invocation, which is a usage rule, not just behavior.

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

Deploy Server

Other Tools