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

With only destructiveHint=true in annotations, the description carries real behavioral weight: it warns that billing starts at boot and is hourly per instance_type, and that exactly one SSH key is supported. It does not explain reversibility (that cleanup requires lambda_terminate_instances) or failure modes, so not a 5.

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

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

Three tight sentences, front-loaded with the highest-stakes fact (cost) before the prerequisite sourcing and the endpoint. No filler or repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, no-output-schema mutation tool, it covers cost, hard prerequisites, and the SSH key constraint well. It omits any pointer to how to observe the launched instance afterward (lambda_get_instance / lambda_list_instances) and doesn't address the image_id/image_family exclusivity left to the schema.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema lacks: which fields are sourced from lambda_list_instance_types, that only capacity-available regions work, and that ssh_key_names must hold exactly one existing key. It says nothing about quantity/name/tags behavior beyond the schema.

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

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

States a specific verb and resource with scope: 'Launch one or more GPU cloud instances.' It is immediately distinguishable from siblings like lambda_terminate_instances and lambda_restart_instances, and the REST endpoint (POST /api/v1/instance-operations/launch) pins the exact operation.

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

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

Gives concrete preconditions and routes the agent to sibling tools for inputs: region/type must come from lambda_list_instance_types (only regions with capacity), and SSH keys must already exist. It does not state when NOT to use this tool or name an alternative launch path, 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.