Skip to main content
Glama

hjarni

by com.hjarni
OverviewDiscussionsAdmin

instructions-get

Read-onlyIdempotent

Get LLM instructions at the specified level. Call with level 'brain' early in conversations to learn user preferences. Optional: level ('brain'|'personal_root'|'container'|'team'), defaults to 'brain' if omitted or blank; the response echoes resolved_level and defaulted_level (true when the level was defaulted). Optional: id (integer, required for 'container' and 'team' levels). 'container' level takes a personal (or shared) container id and returns the full inheritance chain, outermost first; each entry carries a level field ('brain'|'personal_root'|'team'|'container'). Team container ids are not addressable here — read a team note's chain from notes-get, or the team's own instructions with level 'team'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoContainer ID or Team ID (required for 'container' and 'team' levels)
levelNoInstruction level: 'brain' (global), 'personal_root', 'container', or 'team'. Defaults to 'brain' if omitted or blank.brain

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / level / default
      Added value: +"brain"
    • changedInput schema / properties / level / description
      Previous value: -"Instruction level: 'brain' (global), 'personal_root', 'container', or 'team' (required)"New value: +"Instruction level: 'brain' (global), 'personal_root', 'container', or 'team'. Defaults to 'brain' if omitted or blank."
    • changedInput schema / required
      Previous value: -[
-  "level"
-]New value: +[]
  2. Changed1 schema field changed
    • changedInput schema / properties / level / description
      Previous value: -"Instruction level: 'brain' (global), 'personal_root', 'container', or 'team'"New value: +"Instruction level: 'brain' (global), 'personal_root', 'container', or 'team' (required)"
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds substantial behavioral detail beyond that: defaulting behavior and the response fields (resolved_level, defaulted_level), the inheritance chain ordering, and the limitation on team container ids. This gives the agent confidence in what to expect and how to interpret results.

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 a single compact paragraph, but it is information-dense and every sentence adds value. It is not as scannable as a bulleted format, but the structure is logical: purpose, usage tip, parameter details, and a caveat. Slightly long but justified by the richness of content.

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?

With no output schema, the description carries the full burden of explaining the response. It describes the response echoes (resolved_level, defaulted_level) and details the inheritance chain format for 'container' (level field, outermost first). It also covers edge cases like team container ids. Nothing an agent needs to call this tool correctly is missing.

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

Parameters5/5

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

While the schema already documents both parameters and their enums, the description enriches their meaning significantly. It explains how 'id' interacts with 'level' (required for container and team, not for brain), elaborates on the container inheritance returned, and clarifies that team container ids are not valid here. This goes well beyond the schema's basic field descriptions.

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 verb ('Get'), the resource ('LLM instructions'), and specifies the levels ('brain', 'personal_root', 'container', 'team'). It also implies the distinction from sibling tools like notes-get by focusing on the instruction hierarchy. This is a specific, unambiguous purpose that an agent can act on.

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?

Explicit guidance is provided: 'Call with level brain early in conversations to learn user preferences.' It also gives when-not-to-use by pointing to alternatives: team container ids cannot be addressed here, and the agent is directed to notes-get or level 'team'. This level of direction fully equips the agent to choose the correct tool.

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

All hjarni toolsInspect
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.

Resources