Skip to main content
Glama
Sign In

Ignix

by social.ignix
OverviewDiscussionsAdmin

Teach the assistant something

teach_knowledge
Destructive

Add text to this workspace's knowledge base: a policy, an FAQ, prices, how a process works. From then on the Ignix assistant uses it when answering customers on every channel. Each taught text is its own source (source in the answer), so it can be removed alone with delete_knowledge_source. When a rule CHANGES, pass replaces with the old one's source: it is removed in the same step, so the assistant never sees both. Taught passages carry their date and, if two still contradict, the assistant follows the newest.

Input Schema

NameRequiredDescriptionDefault
textYesThe content to learn, in plain text.
labelNoShort name to identify this source later (e.g. "returns policy").
replacesNoOptional: the `source` (from list_knowledge_sources or search_knowledge) of an older taught text this one replaces; it is deleted once this is learned.
workspaceIdNo
idempotencyKeyNoOptional. A unique id for this action (16-128 chars: letters, digits, _ : . -). If you are unsure whether a call went through (timeout, network error), repeat it with the SAME idempotencyKey and the same arguments: you get the original result and nothing is done twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / replaces
      Added value: +{
+  "description": "Optional: the `source` (from list_knowledge_sources or search_knowledge) of an older taught text this one replaces; it is deleted once this is learned.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds genuinely non-obvious behavior: the replacement deletion happens in the same step so both versions never coexist, taught passages are date-stamped, and the newest wins on contradiction. It does not cover permissions or whether workspaceId scoping constrains where the knowledge lands, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences, front-loaded with the core action before the replacement workflow. Every sentence carries decision-relevant information: content scope, propagation to channels, source identity, replacement semantics, and contradiction tie-breaking.

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?

There is no output schema, and the description compensates by explaining that each taught text becomes its own `source` returned in answers. Combined with the replacement and date-precedence behavior, an agent has everything needed to call it correctly and to reason about later retrieval.

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 80%, so the baseline is 3; the description goes further by explaining the semantics and consequence of `replaces` (old source is removed in the same step) and by defining what `source` in an answer refers to. `workspaceId` remains unexplained in both places, a minor gap.

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?

States a concrete verb and resource ("Add text to this workspace's knowledge base") plus example content types (policy, FAQ, prices, process), and names the downstream consumer (the Ignix assistant answering customers on every channel). This clearly separates it from siblings like remember_brand_fact or add_style_examples without the agent needing to open those schemas.

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?

Gives explicit when-to-use context (policy/FAQ/prices/process content) and a precise when-to-do-differently rule: "When a rule CHANGES, pass `replaces` with the old one's source." It also routes the agent to list_knowledge_sources / search_knowledge for the source id and to delete_knowledge_source for standalone removal.

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

All Ignix 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