new_project

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

With no annotations, the description carries the full burden and does meaningful work: it states the project is empty, opens in a new tab, focus switches to it, and crucially that the previous project is not saved. That unsaved-work warning is exactly the kind of behavioral disclosure an agent needs for a destructive-in-effect operation. It does not cover error or permission behavior, 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?

Two short sentences, zero waste, with the core action front-loaded and the important caveat immediately after. Nothing redundant.

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 a zero-param tool with no output schema, the description covers creation, tab behavior, and the unsaved-work caveat. Minor gaps remain (e.g., what happens to the previous project/tab, whether it is closed or left open), but nothing critical to a correct invocation is missing.

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 and 100% schema coverage, so the baseline is 4. There is nothing parameter-wise the description could add.

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 gives a specific verb+resource (create a brand-new empty project) plus meaningful scope detail (in a new tab, switches to it). An agent can easily distinguish this from save_project_as or apply_template. It stops short of explicitly naming a sibling for routing, so it lands at 4 rather than 5.

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?

Usage is implied by the nature of the operation, and the 'Does NOT save the previous project' note usefully flags when an agent should save first. However, there is no explicit when-to-use guidance or named alternative (e.g., save_project_as vs this).

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