Skip to main content
Glama

krusch_context_retrieve

Read-onlyIdempotent

Retrieve project decisions, invariants, bugs, lessons, and drift status by query or category to hydrate AI coding agent context across sessions and avoid repeated mistakes.

Instructions

Hydrate active project invariants, decisions, bugs, lessons, and span-grounded drift status.

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": "krusch_context_retrieve"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoSearch query or "*" for full state hydration
categoryNo
condenseNoEnable 3-tier progressive condensation (auto-enabled on episodic stores >=30 turns)
limit_tokensNo
include_stateNo
include_lineageNoInclude superseded lineage history (auto-enabled on temporal queries)
include_markdownNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully adds what content types come back (invariants, decisions, bugs, lessons, drift status), but says nothing about condensation/token-budget behavior or what 'active' scoping means.

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 front-loaded sentence with no filler. It is dense with unexplained internal terminology, but nothing is redundant.

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 7-parameter tool with no output schema and under-half schema documentation, the description is far too thin. An agent cannot know from it how to shape a query, how condensation or lineage toggles affect results, or what the token limit means in practice.

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

Parameters2/5

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

Schema description coverage is only 43% across 7 parameters, so the description needs to compensate and does not. It never explains query semantics, the category enum (it even omits 'blocker', which the enum supports), condense, limit_tokens, include_lineage, or include_markdown.

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?

Names a specific verb (hydrate) and enumerates the resources returned: invariants, decisions, bugs, lessons, and drift status. It is clearly a read/retrieval tool, distinguishable from siblings like remember/revise, though the phrase 'span-grounded drift status' is jargon an agent may not parse.

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?

No explicit when-to-use guidance and no alternatives named. The definition never says to call this at session start or when resuming work, and the '*' full-hydration mode exists only in the schema, not the description.

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