Skip to main content
Glama

lambda-labs

by io.usefulapi

Launch instance

lambda_launch_instance
Destructive

Launch one or more GPU cloud instances. COSTS MONEY: billing starts as soon as the instance boots (hourly rate per instance_type). Pick region_name + instance_type_name from lambda_list_instance_types (only regions with capacity available), and pass exactly one existing SSH key name in ssh_key_names (create keys in the Lambda dashboard). Lambda Cloud REST: POST /api/v1/instance-operations/launch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoA friendly name for the instance (max 64 chars).
tagsNoKey/value tags to attach to the instance.
hostnameNoCustom hostname (1-63 chars, lowercase alphanumeric and hyphens, pattern ^[a-z0-9][0-9a-z-]{0,62}$).
image_idNoSpecific image id to boot (from lambda_list_images). Mutually exclusive with image_family.
quantityNoHow many instances to launch (default 1). EACH one is billed separately.
user_dataNocloud-init user-data script to run on first boot (max 1MB).
region_nameYesRegion to launch in (e.g. 'us-east-1') — must have capacity for the type.
image_familyNoImage family to boot (latest in family). Mutually exclusive with image_id.
ssh_key_namesYesNames of SSH keys to install (exactly one supported). The key must already exist in your account.
file_system_namesNoNames of existing persistent filesystems to attach.
instance_type_nameYesInstance type to launch (e.g. 'gpu_1x_a100') — from lambda_list_instance_types.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations include destructiveHint=true, but the description adds valuable behavioral context beyond that: 'COSTS MONEY: billing starts as soon as the instance boots (hourly rate per instance_type)'. It also discloses the constraint that exactly one SSH key is supported and keys must already exist. This is useful side-effect information not captured in the annotations.

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 three sentences: purpose, cost warning, and usage guidance. It is front-loaded with the most important information and contains no fluff. Every sentence adds value.

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 has 11 parameters and no output schema, the description focuses on the most critical aspects: required params, cost implication, and prerequisite data. Optional parameters are left to the schema, which fully documents them. This is a reasonable trade-off for a complex launch operation, though a mention of optional capabilities would push it higher.

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

Parameters4/5

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

Schema covers 100% of parameters, so baseline is 3. The description adds meaning by specifying how to select values for region_name and instance_type_name (from lambda_list_instance_types, capacity-aware) and ssh_key_names (exactly one existing key). It also clarifies quantity billing. This enriches the schema without repeating it.

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's function: 'Launch one or more GPU cloud instances.' This is a specific verb+resource, and it distinguishes from sibling tools like terminate, restart, or list operations. The REST endpoint is also provided for clarity.

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 gives explicit guidance on where to obtain parameter values ('Pick region_name + instance_type_name from lambda_list_instance_types'), prerequisites ('only regions with capacity available', 'exactly one existing SSH key'), and a critical caveat (billing starts on boot). It does not explicitly mention alternatives or when-not-to-use, but the context is clear.

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

All lambda-labs toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Each tool targets a distinct resource and action (e.g., list_instances vs. launch_instance vs. terminate_instances). There is no overlap or ambiguity between tools; even similar resources like firewall_rules and firewall_rulesets are clearly differentiated by name and description.

Naming Consistency5/5

All tool names follow the verb_noun pattern with the lambda_ prefix, using lowercase and underscores consistently. The verb clearly indicates the operation (list, get, create, delete, launch, update, restart, terminate), and the noun indicates the resource. Minor pluralization differences (e.g., list_instances vs. get_instance) are conventional and do not break consistency.

Tool Count5/5

15 tools is well-scoped for a GPU cloud management server, covering instances, filesystems, firewall rules, images, instance types, and audit events. Each tool serves a distinct purpose and no unnecessary duplication exists.

Completeness4/5

The instance lifecycle is well covered with launch, get, list, update, restart, and terminate. Filesystem and firewall read operations are present, but firewall rule/ruleset management (create/update/delete) is missing, which is a minor gap that may require working around via the dashboard.

Resources