Skip to main content
Glama

save_decision

Log significant technical choices with rationale and impact, creating a decision history that maintains consistency and guides future work.

Instructions

CRITICAL: Record important architectural and technical decisions for future reference.

MANDATORY: Call this whenever you make significant technical choices. This builds the project's decision history and helps maintain consistency across the codebase.

WHEN TO USE (Always save decisions for):

  • Choosing a framework or library (React vs Vue, Flask vs FastAPI, etc.)

  • Database selection (PostgreSQL vs MongoDB, Redis vs Memcached)

  • Architecture patterns (Microservices vs Monolith, MVC vs Clean Architecture)

  • API design choices (REST vs GraphQL, authentication methods)

  • Infrastructure decisions (Cloud provider, containerization, CI/CD approach)

  • Security implementations (auth strategy, encryption methods)

  • Performance optimizations (caching strategy, database indexing)

  • Any decision that affects the project's direction or maintainability

WHY THIS MATTERS:

  • Other agents (or you later) will understand WHY choices were made

  • Prevents inconsistent approaches across the codebase

  • Documents the evolution of the architecture

  • Helps onboard new team members

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoCategorization tags - e.g., ["architecture", "security", "database"] (optional)
titleYesShort, clear decision title - e.g., "Use JWT for Authentication"
impactNoExpected impact on the project (performance, complexity, maintenance) (optional)
contextNoBackground information that led to this decision (optional)
rationaleYesWHY this decision was made - the reasoning, trade-offs, alternatives considered
project_idNoProject ID from create_project() (optional if project_name or workspace_path provided)
descriptionYesDetailed description of what was decided and how it will be implemented
author_agentNoYour agent_id from register_agent() (optional)
project_nameNoProject name to look up (alternative to project_id)
related_filesNoFile paths affected by this decision (optional)
workspace_pathNoWorkspace directory path (alternative to project_id)
Behavior2/5

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

No annotations are present, so the description must disclose behavioral traits. It only says decisions are recorded for future reference but does not explain what happens on invocation—whether it creates a new record, returns an ID, requires project context, or has side effects. This is a significant gap for a write operation.

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

Conciseness3/5

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

The description is well-structured with headers and bullet lists, but it is verbose with repeated emphasis ('CRITICAL', 'MANDATORY') and a lengthy 'WHY THIS MATTERS' section. It is front-loaded and readable, yet could be more concise.

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?

The description thoroughly covers when and why to use the tool, but omits behavioral expectations such as return values, side effects, or prerequisites. Given no annotations and no output schema, it is sufficient for basic invocation but lacks completeness for a tool with 11 parameters and mutation behavior.

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 all 11 parameters are already documented. The description adds general guidance about what kinds of decisions to save but does not add parameter-level meaning beyond the schema. The baseline of 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 clearly states the tool records important architectural and technical decisions, using a specific verb ('Record') and resource ('decisions'). It effectively distinguishes from sibling retrieval tools like get_project_decisions and search_decisions by emphasizing the act of saving decision history.

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

Usage Guidelines4/5

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

The description provides a detailed 'WHEN TO USE' section with concrete examples (framework choices, database selection, architecture patterns, etc.) and declares it mandatory for significant technical choices. However, it does not mention alternatives or exclusions, so it stops short of a 5.

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/siddiquesahabaj/CoordMCP'

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