Skip to main content
Glama

MyAITwin

by com.lutolearn
OverviewDiscussionsAdmin

add_knowledge

Store a piece of knowledge or a skill in your twin. Automatically tagged and embedded for search. The twin stores two fundamentally different things: knowledge (what the user knows: transcripts, decisions, ideas, observations) and skills (how they express things: their LinkedIn voice, email style, proposal structure, feedback frameworks). Treat skills as a significant moment; they codify craft.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoManual tags to add on top of auto-generated ones
typeYesType for this item. Common types: • skill: how you express something. Your LinkedIn voice, your email style, your proposal structure. The craft layer that shapes knowledge into output. • principle: repeating values, rules, guidelines you apply consistently. • knowledge: expertise areas, domain knowledge, what you know deeply. • idea: concepts, hypotheses, things you're exploring. • voice: writing style, tone, how you communicate. • brand: visual preferences, aesthetic principles, brand rules. • template: reusable structures, formats, scaffolding. • resource: links, documents, references you trust. • reference-record: created via add_reference_record after a creation task. Do not store directly. • meta-principle: surfaced by find_patterns after enough reference records exist. Or any custom type already in the user's schema.
titleNoShort label for this item (optional)
contentYesThe actual content. Write it clearly, in the user's voice.
provenanceNoWhere this content originates. personal = the user's own thinking. employer = from the user's own company/employer (team docs, internal materials, colleagues). client = from or about a specific client (their voice, their deliverables, their brief). external = from outside (articles, reports, third-party authors). organisational is a legacy value being split into employer/client; prefer the more specific value. Default: personal.
source_refNoWhere this came from (document name, URL, etc.)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / provenance / description
      Previous value: -"Where this content originates. personal = the user's own thinking. organisational = from their organisation (e.g. team docs, internal). external = from outside (articles, reports, third-party authors). Default: personal."New value: +"Where this content originates. personal = the user's own thinking. employer = from the user's own company/employer (team docs, internal materials, colleagues). client = from or about a specific client (their voice, their deliverables, their brief). external = from outside (articles, reports, third-party authors). organisational is a legacy value being split into employer/client; prefer the more specific value. Default: personal."
    • changedInput schema / properties / provenance / enum
      Previous value: -[
-  "personal",
-  "organisational",
-  "external"
-]New value: +[
+  "personal",
+  "organisational",
+  "employer",
+  "client",
+  "external"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / content / description
      Previous value: -"The actual content — write it clearly, in the user's voice"New value: +"The actual content. Write it clearly, in the user's voice."
    • changedInput schema / properties / type / description
      Previous value: -"Type for this item. Common types:\n • skill — how you express something. Your LinkedIn voice, your email style, your proposal structure. The craft layer that shapes knowledge into output.\n • principle — repeating values, rules, guidelines you apply consistently.\n • knowledge — expertise areas, domain knowledge, what you know deeply.\n • idea — concepts, hypotheses, things you're exploring.\n • voice — writing style, tone, how you communicate.\n • brand — visual preferences, aesthetic principles, brand rules.\n • template — reusable structures, formats, scaffolding.\n • resource — links, documents, references you trust.\n • reference-record — created via add_reference_record after a creation task. Do not store directly.\n • meta-principle — surfaced by find_patterns after enough reference records exist.\nOr any custom type already in the user's schema."New value: +"Type for this item. Common types:\n • skill: how you express something. Your LinkedIn voice, your email style, your proposal structure. The craft layer that shapes knowledge into output.\n • principle: repeating values, rules, guidelines you apply consistently.\n • knowledge: expertise areas, domain knowledge, what you know deeply.\n • idea: concepts, hypotheses, things you're exploring.\n • voice: writing style, tone, how you communicate.\n • brand: visual preferences, aesthetic principles, brand rules.\n • template: reusable structures, formats, scaffolding.\n • resource: links, documents, references you trust.\n • reference-record: created via add_reference_record after a creation task. Do not store directly.\n • meta-principle: surfaced by find_patterns after enough reference records exist.\nOr any custom type already in the user's schema."
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already indicate a write operation (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds context about auto-tagging and embedding, and the twin's storage model. It does not mention any side effects or limitations, but overall is transparent.

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 front-loaded with the main action and well-structured. Each sentence adds value, but it could be slightly more concise. However, for the complexity, it is appropriate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters all documented in schema, no output schema, the description covers the core usage. It explains the auto-tagging and the two fundamental types. However, it does not describe retrieval or integration with other tools, which is acceptable.

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?

Schema coverage is 100% with descriptions. The description enriches the 'type' parameter by explaining the significance of 'skill' and the distinction between knowledge and skills, adding value beyond the schema.

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 'Store a piece of knowledge or a skill' with a specific verb and resource. It distinguishes between knowledge and skills, and the sibling tools are all different (add_document, add_from_url, etc.), so no confusion.

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?

The description explains when to use the tool: for storing knowledge or skills, with emphasis on skills being significant. It also implicitly excludes storing 'reference-record' types directly. However, it does not explicitly list alternatives or when not to use it.

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

All MyAITwin 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