Skip to main content
Glama
diaz3618

memory-bank-mcp

sequential_thinking

Record numbered thinking steps for structured reasoning, enabling complex problems to be broken into sequential steps with branching and revision. Manage session history, reset when needed, and finalize to persist outcomes to Memory Bank.

Instructions

Record a numbered thinking step for structured reasoning, or reset session history. Use this to break complex problems into sequential steps with optional branching and revision. The raw thought text is NOT returned — only metadata. Call finalize_thinking_session when done to persist outcomes to Memory Bank. Set reset:true to clear thinking history instead of recording a thought.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
thoughtNoThe thinking step content (will NOT be returned in the response). Not required if reset:true.
nextThoughtNeededNoWhether another thinking step is needed after this one. Not required if reset:true.
thoughtNumberNoCurrent thought number (>= 1). Not required if reset:true.
totalThoughtsNoEstimated total number of thoughts (>= 1, auto-adjusts upward). Not required if reset:true.
isRevisionNoWhether this thought revises a previous one
revisesThoughtNoThe thought number being revised (when isRevision is true)
branchFromThoughtNoThe thought number to branch from
branchIdNoIdentifier for the branch
needsMoreThoughtsNoExplicit signal that the total should be increased
sessionIdNoSession identifier to isolate thinking state across tasks
resetNoIf true, resets the session(s) instead of recording a thought. If sessionId is provided, resets only that session.
Behavior5/5

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

With no annotations, the description fully discloses key behavior: 'The raw thought text is NOT returned — only metadata.' It explains the reset mode's effect based on sessionId and describes branching and revision capabilities. This adds significant transparency beyond the input schema.

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?

The description is two sentences plus a final note, all front-loaded with key information. Every sentence adds value: purpose, usage guidance, behavioral note, and reset instruction. No fluff or redundancy.

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 the tool's complexity (11 params, branching, revision, session management) and no output schema, the description covers the two modes, behavioral constraints, and persistence workflow. It lacks details about what 'metadata' is returned, but the overall completeness is strong.

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 coverage is 100%, so the schema already documents each parameter. The description provides overarching context (e.g., thought not returned, reset implications) but does not add meaning substantially beyond the inline schema descriptions. Baseline 3 is appropriate.

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 explicitly states the tool's dual purpose: 'Record a numbered thinking step for structured reasoning, or reset session history.' It clearly distinguishes itself from the sibling tool 'finalize_thinking_session' by mentioning it for persisting outcomes. The verb 'Record' and resource 'thinking step' are specific.

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?

The description provides explicit guidance: 'Use this to break complex problems into sequential steps' and 'Set reset:true to clear thinking history instead of recording a thought.' It also directs the agent to 'Call finalize_thinking_session when done to persist outcomes to Memory Bank,' clearly differentiating from siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/diaz3618/memory-bank-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server