Start the local Studio web UI

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

With no annotations, the description carries the full transparency burden and does so admirably. It discloses key behaviors: 'Only one studio runs at a time,' 'hot reload on file change,' 'auto-generated state machine input controls,' 'event log,' and the 'Instructions for AI' box. It also mentions that re-running create/edit updates the browser instantly, which is a non-obvious behavior.

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 a single dense paragraph but front-loaded with the core purpose. Every sentence adds a useful detail (features, limitations, companion tools). It could be broken into bullets for easier scanning, but no sentence is wasted and the length is justified given the tool's complexity.

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?

Given the tool's complexity and lack of output schema, the description covers most relevant aspects: features, live behavior, single-instance limitation, and connection to other riv_* tools. It does not explicitly state what the tool returns (e.g., the local URL), which would be helpful for an agent, but it covers the essential context for selecting and invoking the tool.

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 description doesn't need to restate parameter basics. It adds value for scenePath by explaining it 'enables the edit+rebuild panel' and mentions the watched path. The `stop` parameter is not described in prose, but the schema description already covers it. The added scenePath context pushes it above the baseline of 3.

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 opens with a specific verb and resource: 'Start a local web UI... for live-previewing and editing a .riv file.' It clearly differentiates the tool from siblings like riv_render_frame or riv_edit by emphasizing interactive editing, timeline, hot reload, and auto-generated controls. The rich feature list makes its purpose unambiguous.

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?

It provides clear context for when to use the tool—for interactive preview and editing—and even references companion tools: 'Re-running riv_create/riv_edit on the watched file updates the browser instantly' and 'fetch those with riv_studio_notes.' However, it does not explicitly name alternatives or say when not to use it, so it falls 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.