Skip to main content
Glama

findabis

by com.findabis
OverviewDiscussionsAdmin

Find cannabis strains

find_strains
Read-onlyIdempotent

Find cannabis strain profiles by name or genetics (Indica, Sativa or Hybrid). Returns up to 25 strains with page URL, slug, genetics and THC and CBD ranges. A strain is a plant lineage, not something a pharmacy dispenses — use find_products for that. Findabis publishes no effects, medical uses or side effects for strains, so none are returned and none should be inferred. For terpenes, flavours and lineage, use get_listing with kind "strain".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoHow many to return, 1-25. Default 10.
queryNoStrain name or nickname, e.g. "Gelato". Omit to browse.
geneticsNoThe strain type: Indica, Sativa or Hybrid.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNo
totalYesHow many matched in all; narrow the query when this exceeds the results
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / genetics / description
      Previous value: -"Indica, Sativa or Hybrid."New value: +"The strain type: Indica, Sativa or Hybrid."
    • addedInput schema / properties / genetics / enum
      Added value: +[
+  "Indica",
+  "Sativa",
+  "Hybrid"
+]
    • changedInput schema / properties / limit / description
      Previous value: -"Default 10."New value: +"How many to return, 1-25. Default 10."
    • changedInput schema / properties / query / description
      Previous value: -"Strain name."New value: +"Strain name or nickname, e.g. \"Gelato\". Omit to browse."
    • addedInput schema / properties / query / maxLength
      Added value: +120
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "note": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "cbdPercent": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "genetics": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "name": {
+            "type": "string"
+          },
+          "slug": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "thcPercent": {
+            "description": "A figure or a range, e.g. \"18-22\"",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "anyOf": [
+              {
+                "format": "uri",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Canonical Findabis page, absolute; null when the listing has no page"
+          }
+        },
+        "required": [
+          "name",
+          "slug",
+          "url",
+          "genetics",
+          "thcPercent",
+          "cbdPercent"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "description": "How many matched in all; narrow the query when this exceeds the results",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "results",
+    "total"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description still adds real behavioral value by capping results at 25 and warning that effects/medical uses/side effects are absent and must not be inferred — an anti-hallucination guarantee not present in the schema or annotations. The enumerated return fields partially duplicate the output schema, keeping this from 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?

Four tight sentences, each doing distinct work: purpose, return shape, sibling disambiguation, and data-absence warning. The most important routing constraint (strain vs. product) is front-loaded before the caveats.

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 an output schema present, return values need no explanation, and the description supplies everything else an agent needs: lookup keys, result cap, sibling routing, and explicit negative scope. Nothing required to invoke it correctly is missing.

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% and all three params (query, genetics, limit) are documented, including the enum values. The description restates the name/genetics lookup but adds no syntax, format or default detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 specific verb and resource ('Find cannabis strain profiles') and immediately bounds the lookup key to name or genetics (Indica/Sativa/Hybrid). It explicitly disambiguates from siblings by declaring a strain is a plant lineage rather than a dispensed product, so an agent can separate it from find_products and get_listing without opening any schema.

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?

Names two concrete alternatives with the condition that selects each: find_products for pharmacy-dispensed items, get_listing with kind "strain" for terpenes, flavours and lineage. It also defines negative scope ('no effects, medical uses or side effects'), removing the most likely wrong-side-of-the-fence questions.

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

All findabis 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