Calera Infinite Context (ICX) — Persistent Memory & Associative Recall

Scoped Memory Recall

icx_recall_scoped

Read-only

Performs semantic search across persistent long-term memory to retrieve grounded facts, relevant citations, and source documents matching a natural language question. Use this tool when answering questions about previously saved project specifications, codebase decisions, user preferences, or documents. Do NOT use for saving new facts (use icx_remember), do NOT use for raw keyword lookup (use icx_search_facts), and do NOT use for exact character-for-character verbatim quotes (use icx_quote_slot). Read-only operation with zero side effects. Requires X-License-Key authentication.

Input Schema

Name	Required	Description
`query`	Yes	Natural language question, concept, or search prompt to recall relevant facts for.
`top_k`	No	Maximum number of grounded facts to retrieve (default: 10, min: 1, max: 50).
`space_id`	No	Optional memory space partition to restrict recall to (e.g. 'default', 'codebase_docs'). Defaults to caller default space.

Output Schema

Name	Required	Description
`count`	Yes	description=Number of grounded facts returned
`facts`	Yes	description=List of recalled grounded facts and citations
`query`	Yes	description=Natural language query submitted
`status`	Yes	description=Recall status (VERIFIED_RECALL \| NO_GROUNDED_FACTS_FOUND)
`space_id`	Yes	description=Target memory space partition
`total_in_space`	Yes	description=Total nodes in active memory space

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the `readOnlyHint` annotation, the description adds critical behavioral context that annotations miss, specifically stating the tool has 'zero side effects' and requires 'X-License-Key authentication.' This is high-value operational information for an AI agent.

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

Conciseness5/5

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

The structure is perfectly front-loaded. It moves seamlessly from the 'what' to the 'when' to the 'what not.' Every sentence serves a critical, decision-making function for the agent, leaving no room for superfluous information.

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?

Given that an output schema exists, the description covers all necessary decisions: the function, its scope, its boundaries relative to siblings, its safety profile, and its operational requirements. It is complete enough for correct selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Since schema coverage is 100%, the baseline is high. The description adds value by defining the nature of the input: the query must be a 'natural language question, concept, or search prompt,' setting the expectation for how the `query` parameter should be used by the agent, which goes beyond the basic string type.

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?

The purpose is explicitly defined as performing 'semantic search across persistent long-term memory.' Crucially, it distinguishes itself from three sibling tools: `icx_remember` (for saving), `icx_search_facts` (for keyword lookup), and `icx_quote_slot` (for verbatim quotes).

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

Usage Guidelines5/5

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

This is exceptionally detailed, providing clear scenarios for use ('answering questions about previously saved project specifications') and explicit exclusionary rules. It names the alternative tools for each failure mode, making it impossible for the AI agent to misapply the tool.

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

All Calera Infinite Context (ICX) — Persistent Memory & Associative Recall 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.