Skip to main content
Glama

create_assistant

Create a new AI assistant profile with a name, provider, model, and system prompt. Reuse or update provider and model later without changing the assistant's identity.

Instructions

Create a new assistant profile.

The provider and model are independent and can be changed later without affecting the assistant's identity, name, or system prompt.

Args: name: Human-readable assistant name. provider: Provider id (must already exist via create_provider). model: Model name for the assistant (provider-specific). assistant_id: Optional explicit id (defaults to a slug of name). description: Short description of the assistant's role. system_prompt: System prompt defining the assistant's behavior. temperature: Sampling temperature 0.0-2.0 (optional). max_tokens: Maximum tokens in the response (optional). capabilities: JSON list of capabilities, e.g. ['swift', 'ios']. permissions: JSON list of permissions, e.g. ['read_files']. metadata: JSON object of arbitrary metadata.

Returns: JSON result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
modelYes
metadataNo{}
providerYes
max_tokensNo
descriptionNo
permissionsNo[]
temperatureNo
assistant_idNo
capabilitiesNo[]
system_promptNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.8/5.0
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 usefully discloses that provider and model are mutable later without affecting identity, name, or system prompt, and flags the provider-existence precondition. However, it says nothing about permissions required, error behavior, or side effects of the write, and 'Returns: JSON result' is only rescued by the output schema.

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?

Uses a front-loaded purpose sentence followed by structured Args/Returns sections. Every argument line earns its place, including the non-obvious provider/model mutability note. Slightly verbose but well organized and easy to scan.

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?

For an 11-parameter creation tool with a rich output schema and no annotations, the description covers purpose, all parameters, mutability, and one key precondition. It omits auth requirements and failure modes, but the presence of an output schema removes the need to explain returns.

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 description coverage is 0%, yet the description documents all 11 parameters with types, ranges (temperature 0.0-2.0), defaults (assistant_id slugged from name), and JSON-format examples for capabilities/permissions/metadata. This fully compensates for the bare schema and adds meaning well beyond it.

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

Purpose4/5

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

States a specific verb and resource ('Create a new assistant profile'), which cleanly separates it from update_assistant, delete_assistant, and create_provider. It does not explicitly name a sibling or explain the boundary, but the intent is unambiguous.

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

Usage Guidelines3/5

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

Usage is implied rather than stated. The only routing hint is the precondition that the provider 'must already exist via create_provider', which tells the agent a prerequisite step exists. There is no explicit guidance on when to choose this over alternatives or what conditions preclude creating an assistant.

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