vegas_project

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

With no annotations, the description carries the full behavioral burden, and it does disclose one real constraint: mutations require project_path sourced from a prior inspect call, which establishes a safe read-before-write workflow. However, it does not identify which actions mutate, whether undo/redo or backup have side effects, or what happens on a missing/invalid project_path, so disclosure is partial for a 14-action dispatcher.

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 tight sentences with the action inventory front-loaded and the parameter prerequisite immediately after; nothing is padded. It loses a point because the first sentence largely restates the schema's action enum, though grouping those values into categories (transport control, cursor) adds mild recognition value beyond the raw list.

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 dispatch tool with 14 actions, nested free-form params, no annotations, and no output schema, the description is thin: it gives no per-action semantics, no indication of which actions mutate the project, and no return information. The project_path prerequisite is the only substantive detail, so an agent cannot confidently call a given action without opening external documentation.

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 description coverage is 0% and the params object is free-form (additionalProperties: {}), so the description must compensate. It documents exactly one parameter (project_path, including the requirement that it match inspect's return value) but says nothing about the per-action params implied by snapshot, set_cursor, set_settings, set_selection, or insert_time, leaving most of the nested object opaque.

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 names concrete verbs grouped by function (inspect, backup, save, undo/redo, transport control, cursor, snapshot) over an implied project resource, and the tool name plus enum make the project-scope clear. It does not, however, explicitly state how this differs from siblings like vegas_timeline or vegas_status, and it omits three enum actions (inspect_settings, set_settings, set_selection, insert_time) from its summary list, so it is clear but not fully distinguishing.

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 one concrete guideline is a prerequisite: mutating actions need params.project_path exactly as returned by inspect — genuinely useful routing information. But it never states when to prefer this dispatcher over the other seven vegas_* siblings, nor which of the 14 actions count as mutating versus read-only, leaving the agent to infer usage boundaries.

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