Load project into the runtime

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

With no annotations, the description must disclose effects. It mentions it's headless, reflects in-memory edits, and returns a snapshot. However, it does not disclose potential side effects such as whether it resets the VM state or overwrites previous load, nor does it describe the snapshot format. These are gaps for a mutation tool.

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?

The description is two sentences, front-loaded with the primary purpose, followed by usage nuance. No wasted words.

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?

The tool is simple (0 params, no output schema), but the description omits details like the snapshot structure and error behavior (e.g., if no project is open). For an agent to use it correctly, knowing what the snapshot contains would be helpful. So it's adequate but not complete.

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?

There are zero parameters, so the description adds no parameter information. Baseline for 0-param tools is 4, and there is nothing else needed.

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?

The description clearly states the verb 'Load', the resource 'open project', and the target 'headless Scratch VM (TurboWarp, JIT)'. It distinguishes from siblings by emphasizing headless operation, which differentiates it from run_project or vm_run. This is specific and actionable.

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?

The description gives context: it's for running and testing without a browser, and it explicitly says to call again after editing to reflect changes. However, it does not explicitly contrast with sibling tools like run_project or vm_run, so the agent has to infer that loading is a prerequisite for running. It lacks explicit exclusions like 'use run_project for execution'.

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