mcp-sequentialthinking-tools

Overview Schema Source Related Servers Discussions Admin

Record one step of sequential reasoning. Optionally include available_tools and recommended_tools; recommendations are validated, not generated, by this server.

sequentialthinking_tools

Record one step of sequential reasoning, optionally validate recommended tools and track branches, helping break complex problems into manageable steps.

Instructions

Input Schema

Name	Required	Description
`thought`	Yes	Current thinking step
`branch_id`	No	Branch identifier
`session_id`	No	Optional history bucket. Defaults to "default".
`is_revision`	No	Whether this revises a thought
`thought_number`	Yes	Current thought number
`total_thoughts`	Yes	Current estimate of total thoughts needed
`available_tools`	No	Optional tool names/descriptions used only to validate recommendations
`remaining_steps`	No	Optional high-level remaining steps
`revises_thought`	No	Thought revised
`recommended_tools`	No	Optional tool plan authored by the model; validated if available_tools is supplied
`branch_from_thought`	No	Thought number this branch starts from
`needs_more_thoughts`	No	Set when the estimate was too low
`next_thought_needed`	Yes	Whether another thought is needed

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.1.1Oct 15, 2026

removedInput schema / properties / available_mcp_tools

Removed value: -{
-  "description": "Array of MCP tool names available for use (e.g., [\"mcp-omnisearch\", \"mcp-turso-cloud\"])",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

addedInput schema / properties / available_tools

Added value: +{
+  "description": "Optional tool names/descriptions used only to validate recommendations",
+  "items": {
+    "anyOf": [
+      {
+        "description": "Tool name",
+        "type": "string"
+      },
+      {
+        "properties": {
+          "description": {
+            "description": "Brief tool description",
+            "type": "string"
+          },
+          "name": {
+            "description": "Tool name",
+            "type": "string"
+          }
+        },
+        "required": [
+          "name"
+        ],
+        "type": "object"
+      }
+    ]
+  },
+  "type": "array"
+}

changedInput schema / properties / branch_from_thought / description

Previous value: -"Branching point thought number"New value: +"Thought number this branch starts from"

removedInput schema / properties / current_step

Removed value: -{
-  "description": "Current step recommendation",
-  "properties": {
-    "expected_outcome": {
-      "description": "What to expect from this step",
-      "type": "string"
-    },
-    "next_step_conditions": {
-      "description": "Conditions to consider for the next step",
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    "recommended_tools": {
-      "description": "Tools recommended for this step",
-      "items": {
-        "properties": {
-          "alternatives": {
-            "description": "Alternative tools that could be used",
-            "items": {
-              "type": "string"
-            },
-            "type": "array"
-          },
-          "confidence": {
-            "description": "0-1 indicating confidence in recommendation",
-            "maximum": 1,
-            "minimum": 0,
-            "type": "number"
-          },
-          "priority": {
-            "description": "Order in the recommendation sequence",
-            "type": "number"
-          },
-          "rationale": {
-            "description": "Why this tool is recommended",
-            "type": "string"
-          },
-          "suggested_inputs": {
-            "additionalProperties": {},
-            "description": "Optional suggested parameters",
-            "type": "object"
-          },
-          "tool_name": {
-            "description": "Name of the tool being recommended",
-            "type": "string"
-          }
-        },
-        "required": [
-          "tool_name",
-          "confidence",
-          "rationale",
-          "priority"
-        ],
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "step_description": {
-      "description": "What needs to be done",
-      "type": "string"
-    }
-  },
-  "required": [
-    "step_description",
-    "recommended_tools",
-    "expected_outcome"
-  ],
-  "type": "object"
-}

changedInput schema / properties / is_revision / description

Previous value: -"Whether this revises previous thinking"New value: +"Whether this revises a thought"

changedInput schema / properties / needs_more_thoughts / description

Previous value: -"If more thoughts are needed"New value: +"Set when the estimate was too low"

changedInput schema / properties / next_thought_needed / description

Previous value: -"Whether another thought step is needed"New value: +"Whether another thought is needed"

removedInput schema / properties / previous_steps

Removed value: -{
-  "description": "Steps already recommended",
-  "items": {
-    "properties": {
-      "expected_outcome": {
-        "description": "What to expect from this step",
-        "type": "string"
-      },
-      "next_step_conditions": {
-        "description": "Conditions to consider for the next step",
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "recommended_tools": {
-        "description": "Tools recommended for this step",
-        "items": {
-          "properties": {
-            "alternatives": {
-              "description": "Alternative tools that could be used",
-              "items": {
-                "type": "string"
-              },
-              "type": "array"
-            },
-            "confidence": {
-              "description": "0-1 indicating confidence in recommendation",
-              "maximum": 1,
-              "minimum": 0,
-              "type": "number"
-            },
-            "priority": {
-              "description": "Order in the recommendation sequence",
-              "type": "number"
-            },
-            "rationale": {
-              "description": "Why this tool is recommended",
-              "type": "string"
-            },
-            "suggested_inputs": {
-              "additionalProperties": {},
-              "description": "Optional suggested parameters",
-              "type": "object"
-            },
-            "tool_name": {
-              "description": "Name of the tool being recommended",
-              "type": "string"
-            }
-          },
-          "required": [
-            "tool_name",
-            "confidence",
-            "rationale",
-            "priority"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "step_description": {
-        "description": "What needs to be done",
-        "type": "string"
-      }
-    },
-    "required": [
-      "step_description",
-      "recommended_tools",
-      "expected_outcome"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

addedInput schema / properties / recommended_tools

Added value: +{
+  "description": "Optional tool plan authored by the model; validated if available_tools is supplied",
+  "items": {
+    "properties": {
+      "alternatives": {
+        "description": "Alternative tool names",
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "confidence": {
+        "description": "Optional 0-1 confidence score",
+        "maximum": 1,
+        "minimum": 0,
+        "type": "number"
+      },
+      "priority": {
+        "description": "Optional execution order hint",
+        "minimum": 1,
+        "type": "number"
+      },
+      "rationale": {
+        "description": "Why this tool may help",
+        "type": "string"
+      },
+      "suggested_inputs": {
+        "additionalProperties": {},
+        "description": "Optional suggested tool arguments",
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "tool_name": {
+        "description": "Name of the tool being recommended",
+        "type": "string"
+      }
+    },
+    "required": [
+      "tool_name"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedInput schema / properties / remaining_steps / description

Previous value: -"High-level descriptions of upcoming steps"New value: +"Optional high-level remaining steps"

changedInput schema / properties / revises_thought / description

Previous value: -"Which thought is being reconsidered"New value: +"Thought revised"

addedInput schema / properties / session_id

Added value: +{
+  "description": "Optional history bucket. Defaults to \"default\".",
+  "type": "string"
+}

changedInput schema / properties / thought / description

Previous value: -"Your current thinking step"New value: +"Current thinking step"

changedInput schema / properties / total_thoughts / description

Previous value: -"Estimated total thoughts needed"New value: +"Current estimate of total thoughts needed"

changedInput schema / required

Previous value: -[
-  "available_mcp_tools",
-  "thought",
-  "next_thought_needed",
-  "thought_number",
-  "total_thoughts"
-]New value: +[
+  "thought",
+  "thought_number",
+  "total_thoughts",
+  "next_thought_needed"
+]

Changed7 schema fields changedv1.0.0Jan 2, 2026
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- changedInput schema / properties / branch_from_thought / type
```
Previous value: -"integer"New value: +"number"
```
- addedInput schema / properties / current_step / properties / recommended_tools / items / properties / suggested_inputs / additionalProperties
```
Added value: +{}
```
- addedInput schema / properties / previous_steps / items / properties / recommended_tools / items / properties / suggested_inputs / additionalProperties
```
Added value: +{}
```
- changedInput schema / properties / revises_thought / type
```
Previous value: -"integer"New value: +"number"
```
- changedInput schema / properties / thought_number / type
```
Previous value: -"integer"New value: +"number"
```
- changedInput schema / properties / total_thoughts / type
```
Previous value: -"integer"New value: +"number"
```
First observedAug 18, 2025

TDQS

C2.7/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does disclose one genuinely non-obvious trait: recommendations are validated, not generated, by this server. However, it omits persistence behavior, whether steps accumulate in a session, and what the recorded step does for subsequent calls.

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?

Compact and front-loaded: the core action leads, and the optional-input/validation caveat follows in one clause. No filler sentences, though the text largely mirrors the title.

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

Completeness3/5

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

For a 13-parameter tool with no annotations and no output schema, the description covers purpose and one behavioral trait but says nothing about session persistence, iterative invocation, or return behavior. The rich schema compensates for the parameter gaps, keeping this at a minimum-viable level.

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 all 13 parameters, making a 3 the baseline. The description adds only a reinforcing note that recommendations are validated against available_tools rather than invented, which the schema already implies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this versus the history siblings, no note that it is meant to be invoked repeatedly to build a chain, and no prerequisites. The only usage-adjacent content is that available_tools and recommended_tools are optional, which is parameter guidance rather than when-to-use guidance.

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

Deploy Server

Record one step of sequential reasoning. Optionally include available_tools and recommended_tools; recommendations are validated, not generated, by this server.

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools