Skip to main content
Glama

chat_create_session

Create a new stateful conversation session for multi-turn cloud architecture design. Useful when each design turn depends on the prior one, enabling iterative refinement with frozen constraints and budget or compliance settings.

Instructions

Create a new stateful architecture-design conversation session.

Returns {'session_id': <12-char hex>}. The session_id is the handle for subsequent chat_send / chat_delete_session calls.

When to use: Multi-turn architecture design where each turn depends on the prior one (e.g. 'design it', 'now add a cache', 'now move to GCP'). For single-shot design use design_architecture; for one-shot edits of an existing spec use modify_architecture.

Behavior: Writes a new session file to the session store (persisted on disk). Does not call the LLM — the first LLM call happens on the first chat_send. Constraints are frozen at session creation and apply to every turn.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
providerNoDefault cloud provider for the session. Every subsequent `chat_send` within this session uses this provider unless overridden in the message.aws
budget_monthlyNoOptional monthly budget cap (USD). Applied across all design turns within the session — the architect will bias toward fitting under it.
complianceNoOptional compliance frameworks enforced across the session's design turns. Values: 'hipaa', 'pci-dss', 'soc2', 'fedramp', 'gdpr'.
Behavior5/5

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

No annotations provided, so description must cover behavior. It states 'Writes a new session file to the session store (persisted on disk)' and 'Does not call the LLM — the first LLM call happens on the first chat_send.' Also specifies the return value format. This fully discloses operational traits.

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 7 sentences, well-structured with front-loaded main purpose, then return format, usage guidelines, and behavioral details. Every sentence adds value; no redundancy or fluff.

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?

Given no output schema, the description explains the return value ('session_id'). It covers purpose, when to use, behavioral details, parameter context, and constraints. For a tool with 3 optional params, this is fully complete and leaves no gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds contextual meaning: provider can be overridden per message, budget_monthly is a cap applied across turns, and compliance frameworks are enforced across the session. This goes beyond the schema's property descriptions.

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 'Create a new stateful architecture-design conversation session.' The verb 'create' and resource 'session' are specific. It differentiates from sibling tools by mentioning stateful and multi-turn context (vs single-shot design_architecture and modify_architecture).

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 tells when to use this tool: 'Multi-turn architecture design where each turn depends on the prior one.' Provides clear alternatives: 'For single-shot design use design_architecture; for one-shot edits of an existing spec use modify_architecture.' Also explains constraint freezing at creation.

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/xmpuspus/cloudwright'

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