Skip to main content
Glama
shivyadavus

Open Kioku

by shivyadavus
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Open Kioku Build Compressed Context

build_compressed_context

Compress source snippets into short handles to cut token count for prompt-limited tasks, then expand them on demand with retrieve_context.

Instructions

Build a compressed context pack with short handles instead of full source snippets, reducing token count for prompt-constrained scenarios. Use retrieve_context with the returned handles to expand original snippets on demand. Use when a context pack is needed but prompt token budget is constrained. Returns compressed references with short handles instead of full source snippets, significantly reducing token count. Call retrieve_context later with a handle to expand the original snippet. Do NOT use when full inline context is acceptable (use build_context_pack) or when only test targets are needed (use find_tests_for_change). This tool writes reusable context handles under the .ok data directory and is not idempotent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesA natural language description of the task to gather compressed context for.
limitNoMaximum number of context items to compress. Defaults to 20. Higher values increase completeness but also stored handle count.
formatNoOutput format. 'json' returns structured handle objects, 'toon' returns token-optimized notation with handles. Defaults to 'json' when omitted.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
valueNoWrapped non-object output, used for Markdown, TOON, or scalar responses.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.2.3
    • changedInput schema / properties / format / description
      Previous value: -"The output format."New value: +"Output format. 'json' returns structured handle objects, 'toon' returns token-optimized notation with handles. Defaults to 'json' when omitted."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of context items. Defaults to 20."New value: +"Maximum number of context items to compress. Defaults to 20. Higher values increase completeness but also stored handle count."
    • changedInput schema / properties / task / description
      Previous value: -"A natural language description of the task."New value: +"A natural language description of the task to gather compressed context for."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "The MCP structuredContent object returned by this Open Kioku tool. Most tools expose their JSON fields directly; string or scalar tool outputs are wrapped as {\"value\": ...}.",
+  "properties": {
+    "value": {
+      "description": "Wrapped non-object output, used for Markdown, TOON, or scalar responses."
+    }
+  },
+  "type": "object"
+}
  2. Changed3 schema fields changedv2.0.3
    • changedInput schema / properties / format / description
      Previous value: -"Output format"New value: +"The output format."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of context items. Defaults to 20."
    • changedInput schema / properties / task / description
      Previous value: -"Natural language task description"New value: +"A natural language description of the task."
  3. First observedv2.0.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations show readOnlyHint=false and idempotentHint=false; the description goes further by specifying that the tool writes reusable context handles under the .ok data directory and is not idempotent. No contradiction with annotations.

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?

The description is well-structured with a clear main purpose, usage guidelines, and exclusions. However, it contains some redundancy (e.g., 'reducing token count' appears twice) which makes it slightly less concise.

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 the tool has 3 parameters, an output schema exists, and the description covers usage, side effects, and alternatives, the description is complete. No significant gaps for an agent to invoke correctly.

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 baseline is 3. The description does not add further meaning to parameters beyond what the schema already provides. Schema documents task, limit, and format adequately.

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 description clearly states the tool builds a compressed context pack with short handles instead of full snippets, reducing token count. It distinguishes from sibling tools like build_context_pack and find_tests_for_change.

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?

Explicitly provides when to use (prompt-constrained scenarios) and when not to use (when full inline context is acceptable, or when test targets are needed). Names specific alternative tools (build_context_pack, find_tests_for_change) and companion tool (retrieve_context).

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

Deploy Server

Other Tools