WebLens

deep_research

Multi-step research in one call: plans sub-questions, searches each, fetches and dedupes sources, and synthesizes an answer with inline [n] citations, key findings, and gaps. Tiers: quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard. Price: quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard.

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": "deep_research"
  }
}

Input Schema

Name	Required	Description	Default
`depth`	No	quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard.	standard
`query`	Yes	The research question

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 13, 2026

addedInput schema / properties / depth / default
```
Added value: +"standard"
```

changedInput schema / properties / depth / description

Previous value: -"Research tier: quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard."New value: +"quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard."

addedInput schema / properties / depth / example
```
Added value: +"standard"
```

changedInput schema / properties / query / description

Previous value: -"The research question (1-500 chars)"New value: +"The research question"

addedInput schema / properties / query / example

Added value: +"How are AI agents using micropayments in 2026?"

addedInput schema / properties / query / maxLength
```
Added value: +500
```
addedInput schema / properties / query / minLength
```
Added value: +1
```

Changed2 schema fields changedOct 13, 2026

changedInput schema / properties / depth / description

Previous value: -"Research tier: standard = 3 sub-questions / 8 sources ($0.20); deep = 5 / 12 ($0.35). Default: standard"New value: +"Research tier: quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard."

changedInput schema / properties / depth / enum

Previous value: -[
-  "standard",
-  "deep"
-]New value: +[
+  "quick",
+  "standard",
+  "deep"
+]

First observedAug 4, 2026

TDQS

A3.7/5.0

Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does disclose the internal pipeline, the synthesized output structure, and per-tier cost/effort. Gaps remain around latency (multi-step search is presumably slow), timeouts, and failure behavior, so it is not fully transparent.

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

Conciseness2/5

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

The tier/price block is duplicated verbatim within the same description ('Tiers: ...' immediately followed by 'Price: ...' with identical content), which is wasteful and makes the description feel machine-assembled. The opening pipeline sentence is strong and front-loaded, but the redundancy is a clear structural flaw.

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

Completeness4/5

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

With no output schema, the description does describe the return shape (citations, key findings, gaps), which is the key missing piece for a research tool. Cost and effort tiers are complete. Only latency/error expectations are absent, a minor gap for a 2-parameter tool.

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 coverage is 100%, and the description's tier breakdown is verbatim identical to the depth parameter's schema description, adding no new meaning. The query parameter gets no elaboration beyond the schema's example. Baseline 3 applies.

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?

Specific verb chain (plans, searches, fetches, dedupes, synthesizes) and resource (multi-step research) that an agent can distinguish from single-shot siblings like search_web or answer_question. The output artifact is also named (inline [n] citations, key findings, gaps), so the tool's identity is unambiguous.

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

Usage Guidelines3/5

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

Tier selection is well covered (quick/standard/deep with cost and effort), but there is no guidance on when to reach for deep_research versus answer_question or search_web. Usage is implied by the name and pipeline description rather than stated with alternatives or exclusions.

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

All WebLens 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.