Liminal

search

Read-onlyIdempotent

Search your saved answer titles; newest 1000 runs, at most 20 matches.

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>",
      "context": "<context>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description
`query`	Yes
`context`	Yes	User's goal in one short sentence; no personal data or secrets.
`llm_model`	No	Your exact model id for analytics, or "unknown"; never guess.

Output Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedInput schema / required

Previous value: -[
-  "query",
-  "context",
-  "llm_model"
-]New value: +[
+  "query",
+  "context"
+]

Changed2 schema fields changedNov 4, 2026

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."

AddedNov 1, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description does add genuine behavioral facts beyond that: matching is against titles, only the newest 1000 runs are scanned, and the result cap is 20. It stops short of saying how matching works (substring, prefix, ranking) or whether truncation is signalled.

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?

A single clause packs the scope, corpus window, and result cap with no filler, and the key constraint is front-loaded. The semicolon construction is slightly terse but readable.

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?

An output schema exists, so return values need not be explained. With annotations covering the safety profile and the description covering corpus, recency window, and match cap, an agent has everything needed to decide to call it and to interpret an empty result.

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%, above the baseline threshold, and two of three parameters carry their own descriptions. The description adds one useful clarification, that the query is matched against titles rather than full answer text, but it says nothing about the required query format or the context parameter's intended wording.

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 states a specific verb ("Search") and a specific resource ("your saved answer titles"), plus the corpus scope. It does not differentiate itself from siblings such as research or read, but the message is clear enough that an agent knows what corpus is being queried.

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 explicit when-to-use or when-not-to-use guidance and no prerequisite stated. The phrase "your saved answer titles" implies the appropriate context, but the agent is left to infer whether to search here versus running research or read on the same material.

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

All Liminal 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.