Skip to main content
Glama

Liminal

solve

Frame and answer a non-trivial decision or multi-step request in one call; skip simple lookups. 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>"
    },
    "name": "solve"
  }
}

Input Schema

NameRequiredDescriptionDefault
contextNo
task_idNo
questionYesthe complete request
llm_modelNoYour exact model id for analytics, or "unknown"; never guess.
follow_up_ofNoresult_id this continues

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
      -  "question",
      -  "llm_model"
      -]New value: +[
      +  "question"
      +]
  2. Changed1 schema field changed
    • 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"
      -]New value: +[
      +  "question",
      +  "llm_model"
      +]
  4. Changed20 schema fields changed
    • removedInput schema / properties / checkpoint_id
      Removed value: -{
      -  "default": "",
      -  "title": "Checkpoint Id",
      -  "type": "string"
      -}
    • removedInput schema / properties / context / default
      Removed value: -""
    • removedInput schema / properties / context / title
      Removed value: -"Context"
    • removedInput schema / properties / context_brief_id
      Removed value: -{
      -  "default": "",
      -  "title": "Context Brief Id",
      -  "type": "string"
      -}
    • removedInput schema / properties / depth
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "enum": [
      -        "shallow",
      -        "standard",
      -        "deep"
      -      ],
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Depth"
      -}
    • removedInput schema / properties / follow_up_of / default
      Removed value: -""
    • addedInput schema / properties / follow_up_of / description
      Added value: +"result_id this continues"
    • removedInput schema / properties / follow_up_of / title
      Removed value: -"Follow Up Of"
    • removedInput schema / properties / max_reduction_depth
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "integer"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Max Reduction Depth"
      -}
    • removedInput schema / properties / preference_policy
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "additionalProperties": true,
      -      "type": "object"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Preference Policy"
      -}
    • addedInput schema / properties / question / description
      Added value: +"the complete request"
    • removedInput schema / properties / question / title
      Removed value: -"Question"
    • removedInput schema / properties / resources
      Removed value: -{
      -  "default": "",
      -  "title": "Resources",
      -  "type": "string"
      -}
    • removedInput schema / properties / task_id / default
      Removed value: -""
    • removedInput schema / properties / task_id / title
      Removed value: -"Task Id"
    • removedInput schema / properties / tool_manifest
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "items": {
      -        "additionalProperties": true,
      -        "type": "object"
      -      },
      -      "type": "array"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Tool Manifest"
      -}
    • removedInput schema / properties / trace
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "enum": [
      -        "off",
      -        "summary",
      -        "verbose"
      -      ],
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Trace"
      -}
    • removedInput schema / properties / user_id
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "User Id"
      -}
    • removedInput schema / properties / verbose
      Removed value: -{
      -  "default": false,
      -  "title": "Verbose",
      -  "type": "boolean"
      -}
    • removedInput schema / title
      Removed value: -"solveArguments"
  5. First observed

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. Beyond "in one call" it says nothing about cost, latency, side effects, whether results are persisted (a follow_up_of result_id is implied by the schema but unexplained), or what shape the answer takes; for a heavyweight generative tool with no output schema this is a substantial gap.

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 action and immediately followed by the exclusion and the escalation path. The "More args:" fragment is terse to the point of being cryptic, but nothing is wasted.

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?

For a complex, five-parameter reasoning/orchestration tool with no annotations and no output schema, the description should at minimum say what comes back and how follow_up_of and result_id relate. Neither is addressed, and the only completeness aid is an indirection to another 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 60% and the description adds no per-parameter meaning; instead it outsources parameter discovery to a separate get_capabilities call. That pointer is mildly useful, but the description does not clarify context, task_id, or how follow_up_of chains to a prior result_id, so it operates at baseline.

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?

"Frame and answer a non-trivial decision or multi-step request in one call" gives a concrete verb pair (frame/answer) and a clearly scoped resource class, which distinguishes it from lookup-style siblings. It stops short of saying what the tool actually produces or what kinds of decisions qualify, leaving some ambiguity about the boundary of "non-trivial."

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

Usage Guidelines4/5

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

"skip simple lookups" is an explicit exclusion, and "More args: get_capabilities(tool=...)" routes the agent to a specific sibling for deeper configuration. It does not name alternatives for other complex tasks (e.g. research), but the when-not guidance is stated rather than implied.

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.