Skip to main content
Glama

Liminal

research

Web research question answered with fetched, cited findings. More args: get_capabilities(tool=...).

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": {
      "question": "<question>",
      "context": "<context>"
    },
    "name": "research"
  }
}

Input Schema

NameRequiredDescriptionDefault
contextYesUser's goal in one short sentence; no personal data or secrets.
questionYes
llm_modelNoYour exact model id for analytics, or "unknown"; never guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
      -  "question",
      -  "context",
      -  "llm_model"
      -]New value: +[
      +  "question",
      +  "context"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / context / description
      Previous value: -"Describe the user's goal in one short sentence. Omit personal data and secrets."New value: +"User's goal in one short sentence; no personal data or secrets."
    • changedInput schema / properties / llm_model / description
      Previous value: -"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."New value: +"Your exact model id for analytics, or \"unknown\"; never guess."
  3. Changed2 schema fields changed
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "question",
      -  "context"
      -]New value: +[
      +  "question",
      +  "context",
      +  "llm_model"
      +]
  4. Changed5 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Describe the user's goal in one short sentence. Omit personal data and secrets.",
      +  "type": "string"
      +}
    • removedInput schema / properties / max_depth
      Removed value: -{
      -  "default": 3,
      -  "title": "Max Depth",
      -  "type": "integer"
      -}
    • removedInput schema / properties / question / title
      Removed value: -"Question"
    • changedInput schema / required
      Previous value: -[
      -  "question"
      -]New value: +[
      +  "question",
      +  "context"
      +]
    • removedInput schema / title
      Removed value: -"researchArguments"
  5. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it discloses almost nothing: no indication of cost, latency, rate limits, network access, or whether results are cached or repeatable. "Fetched, cited findings" hints that it retrieves web sources and attributes them, but the depth of research and its side effects are unstated.

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 core purpose, with no filler or repetition. The second sentence is a terse documentation pointer that earns its place only marginally but does not bloat the definition.

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

Completeness3/5

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

With no output schema and no annotations, the description should do more, yet it at least indicates the shape of the return value (fetched, cited findings) and where to discover additional arguments. It leaves critical gaps for a research call: expected cost or duration, source depth, and when a cheaper sibling like search would suffice.

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 67%: context and llm_model are documented in the schema, and question, while undescribed, is self-explanatory from the tool purpose. The description adds no parameter meaning itself, aside from the vague "More args" pointer suggesting additional options exist beyond the three in the schema.

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

Purpose4/5

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

The description pairs a specific resource ("Web research question") with a specific output ("fetched, cited findings"), so an agent knows this performs web research and returns sourced results rather than raw pages. It does not differentiate the tool from siblings such as search, fetch, or solve, which keeps it at 4 rather than 5.

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 choose this over search, fetch, or solve, and no stated preconditions or exclusions. The only routing hint is "More args: get_capabilities(tool=...)", which points to more documentation rather than explaining usage; the implied context (research questions) is left for the agent to infer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.