Skip to main content
Glama
Perplexity Web MCP

Perplexity Web MCP

by jacob-bd

pplx_glm53

GLM 5.3 — Z.ai's newest model with thinking always enabled. COSTS 1 PRO SEARCH QUERY.

Instructions

GLM 5.3 — Z.ai's newest model with thinking always enabled. 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_glm53"
  }
}

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 supplied, the description carries the full burden, and it does disclose two genuinely useful behaviors: thinking is always on (no way to disable it) and each call spends one pro search query. It omits latency expectations, whether the call is stateful outside conversation_id, and any auth/precondition details.

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 ending on the cost constraint — no wasted wording. The brevity is efficient rather than padded, though it shades into under-specification elsewhere.

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 needn't be described, and the cost/thinking notes cover the behavioral basics. But for a tool sitting in a large family of near-identical model selectors with three entirely undocumented parameters, the definition leaves too much for the agent to infer.

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, source_focus, and conversation_id get no explanation at all. An agent cannot learn from this text what source_focus accepts or how conversation_id threads requests, leaving the schema's bare types as the only source.

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 ("GLM 5.3 — Z.ai's newest model") and a key trait (thinking always enabled), which lets an agent distinguish it from sibling model tools by name. However, it never states the actual action — no verb like "query" or "ask" — so the purpose is only implied by the model label and the trailing cost note about a search query.

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?

There is no guidance on when to pick this model over the ~20 sibling model tools (e.g. pplx_gpt61_sol, pplx_claude_opus_think), nor on what kinds of questions suit it. The only implicit signal is the cost warning, which hints at using it sparingly but does not state an alternative.

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