context-crystal

Overview Schema Source Related Servers Discussions Admin

crystal_search

Search, list, and filter crystals by status, author, date, text query, lessons, tasks, leases, and paths, or provide crystal_id to inspect DAG transition nodes.

Instructions

Search and list crystals in the cave with multi-dimensional filtering, or search and inspect DAG transition nodes when crystal_id is provided.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "crystal_search"
  }
}

Input Schema

Name	Required	Description
`all`	No	When crystal_id is provided, return all matching nodes without pagination cap
`kind`	No	When crystal_id is provided, filter nodes by kind
`sort`	No	Sort order: recent (default), oldest, name
`aging`	No	Filter by aging category (active, solid, stale)
`limit`	No	Maximum number of results to return per page (default: 20; 0 to uncap)
`query`	No	Free-text search query across crystal ID, title, intent, DAG nodes, lessons, and artifacts
`since`	No	Filter crystals active on or after ISO-8601 date/datetime or relative expression (today, yesterday, 1d, 7d)
`until`	No	Filter crystals active on or before ISO-8601 date/datetime or relative expression
`author`	No	Filter by author entity ID
`offset`	No	Result offset for pagination (default: 0)
`status`	No	Filter by goal status
`crystal_id`	No	When provided, scopes search or listing to DAG nodes within the specified crystal, returning matching nodes
`has_lessons`	No	Filter crystals with recorded lessons learned
`json_output`	No	Output structured JSON array instead of text table (default: false)
`touching_path`	No	Match leases or artifacts referencing the specified filesystem path or URI
`has_open_tasks`	No	Filter crystals with incomplete acceptance criteria
`include_archived`	No	Include crystals in cold storage (default: false)
`has_active_leases`	No	Filter crystals holding active transient resource leases

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.3.0Oct 28, 2026

addedInput schema / properties / all

Added value: +{
+  "description": "When crystal_id is provided, return all matching nodes without pagination cap",
+  "type": "boolean"
+}

addedInput schema / properties / crystal_id

Added value: +{
+  "description": "When provided, scopes search or listing to DAG nodes within the specified crystal, returning matching nodes",
+  "type": "string"
+}

addedInput schema / properties / kind

Added value: +{
+  "description": "When crystal_id is provided, filter nodes by kind",
+  "enum": [
+    "human_prompt",
+    "agent_reasoning",
+    "tool_execution",
+    "checkpoint",
+    "branch",
+    "resolution"
+  ],
+  "type": "string"
+}

Addedv1.1.0Oct 3, 2026

TDQS

B3.4/5.0

Behavior2/5

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

No annotations exist, so the description carries the full burden, yet it never states this is a read-only operation, what the two modes return, or how pagination/uncapped behavior works. The schema covers defaults like limit=20 and offset=0, but the description adds no behavioral context beyond repeating the mode switch.

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 well-formed sentence that front-loads the primary mode and appends the conditional mode. Nothing is wasted, though one more sentence on mode-scoped parameters would have earned its place.

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 18 parameters, no annotations, and no output schema, an agent still lacks any description of what either mode returns or how results differ between crystal listing and node listing. The rich input schema offsets much of this, keeping it at minimum-viable rather than inadequate.

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 description coverage is 100%, so every one of the 18 parameters is already documented in structured form, including conditional params like kind and all that only apply with crystal_id. The description adds only the phrase 'multi-dimensional filtering' and does not explain parameter interactions (e.g., that kind/all are mode-scoped), so the baseline 3 applies.

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 names a specific verb pair (search/list) and resource (crystals in the cave), and explicitly declares a second mode (DAG transition nodes) selected by crystal_id. That dual-mode framing lets an agent distinguish it from siblings like crystal_triage or crystal_stats, though it never names an alternative directly.

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?

It gives a clear routing rule: omit crystal_id to search/list crystals, provide crystal_id to inspect DAG nodes within that crystal. There are no exclusions or prerequisite/pitfall notes, which keeps it below 5.

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