Skip to main content
Glama

Blackwood State

by io.github.Blackwood-State
OverviewDiscussionsAdmin

Sentiment

blackwood_text_sentiment
Read-onlyIdempotent

Use when you need sentiment analysis of text such as reviews, comments or headlines in English. Do not use for neutral or emotion labels, non-English text or aspect-level sentiment. Returns JSON with the sentiment of English text (positive or negative with a confidence score) from DistilBERT SST-2 on Workers AI, for one text or a batch of up to 20 for 0.004 USDC per call. Typical response time 1500 ms (p95). Category: Inference.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNoOne English text to classify, e.g. The checkout was fast (up to 2000 characters)
textsNoOr a batch of up to 20 English texts, e.g. ["Great support", "Broken on arrival"]
response_formatNoconcise (the default when omitted) keeps the JSON short: long fields such as base64 images or audio come back as separate image/audio content blocks and other long strings are cut with a marker; detailed returns the full JSON

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "model": {
-        "type": "string"
-      },
-      "results": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "label": {
-              "enum": [
-                "positive",
-                "negative"
-              ],
-              "type": "string"
-            },
-            "negative": {
-              "type": "number"
-            },
-            "positive": {
-              "type": "number"
-            },
-            "score": {
-              "type": "number"
-            },
-            "text": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "text",
-            "label",
-            "score",
-            "positive",
-            "negative"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      }
-    },
-    "required": [
-      "results",
-      "model"
-    ],
-    "type": "object"
-  },
-  {
-    "description": "x402 PaymentRequired (returned with isError when payment is needed)",
-    "properties": {
-      "accepts": {
-        "items": {
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "error": {
-        "type": "string"
-      },
-      "extensions": {
-        "type": "object"
-      },
-      "resource": {
-        "type": "object"
-      },
-      "x402Version": {
-        "type": "integer"
-      }
-    },
-    "required": [
-      "x402Version",
-      "accepts"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "model": {
+        "type": "string"
+      },
+      "next": {
+        "additionalProperties": false,
+        "description": "Suggested next paid call in the same family (call it in a loop when the task continues)",
+        "properties": {
+          "method": {
+            "enum": [
+              "GET",
+              "POST"
+            ],
+            "type": "string"
+          },
+          "sample": {
+            "description": "Free fixed sample of the whole family",
+            "type": "string"
+          },
+          "service": {
+            "description": "Service id of the suggested next paid call",
+            "type": "string"
+          },
+          "tool": {
+            "description": "MCP tool name of the same call",
+            "type": "string"
+          },
+          "url": {
+            "description": "Paid route of the next call",
+            "type": "string"
+          },
+          "useWhen": {
+            "description": "When the next call is the right one",
+            "type": "string"
+          }
+        },
+        "required": [
+          "service",
+          "tool",
+          "method",
+          "url",
+          "useWhen",
+          "sample"
+        ],
+        "type": "object"
+      },
+      "results": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "label": {
+              "enum": [
+                "positive",
+                "negative"
+              ],
+              "type": "string"
+            },
+            "negative": {
+              "type": "number"
+            },
+            "positive": {
+              "type": "number"
+            },
+            "score": {
+              "type": "number"
+            },
+            "text": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "text",
+            "label",
+            "score",
+            "positive",
+            "negative"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "results",
+      "model"
+    ],
+    "type": "object"
+  },
+  {
+    "description": "x402 PaymentRequired (returned with isError when payment is needed)",
+    "properties": {
+      "accepts": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "error": {
+        "type": "string"
+      },
+      "extensions": {
+        "type": "object"
+      },
+      "resource": {
+        "type": "object"
+      },
+      "x402Version": {
+        "type": "integer"
+      }
+    },
+    "required": [
+      "x402Version",
+      "accepts"
+    ],
+    "type": "object"
+  }
+]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: the backing model (DistilBERT SST-2 on Workers AI), cost (0.004 USDC per call), batch ceiling of 20, and p95 latency of 1500 ms. Pricing and latency disclosure is behaviorally important for an agent deciding whether to call.

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?

Usage guidance is front-loaded and the operational facts are packed into one dense sentence with no filler. It loses a point for mild repetition ('English text' appears three times), but every sentence still carries information.

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 not be re-explained, yet the description still summarizes the positive/negative-with-confidence output. Combined with model, cost, latency, batch limit, and exclusions, an agent has everything needed to invoke it correctly.

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%, so the schema already documents text, texts, and response_format, including the enum semantics for response_format. The description restates the one-or-batch-of-20 choice but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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+resource ('sentiment analysis of text') and scopes the input domain ('reviews, comments or headlines in English'). It is clearly separable from siblings like blackwood_text_summarize and blackwood_text_translate 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?

Explicitly names when-not-to-use cases ('neutral or emotion labels, non-English text or aspect-level sentiment'), which routes the agent away from this tool for the wrong sentiment variants. This is exactly the when/when-not guidance the dimension asks for.

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

All Blackwood State toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources