live_eval

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

With no annotations, the description carries the full burden and does so well: it discloses available globals, the install-time gating flag, the error-handling hazard (a modal Scripting Error dialog pops on throw or on calling a non-existent host member), and the guard idiom (typeof check). This is exactly the operational context an agent needs before invoking.

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?

Front-loads purpose, then prerequisites, then the critical caveat. Dense but every sentence adds value; the warning about the modal dialog is slightly long-winded but warranted given the failure mode.

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 two-parameter tool with no output schema, the description covers purpose, gating condition, globals, an example, and failure behavior. Return value is only loosely characterized ('return the result'), which is a minor gap but the absence of an output schema makes that acceptable.

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 50%: `code` is documented in the schema, but `depth` has no schema description. The description compensates by explaining that host objects are 'described to a depth', giving the parameter meaning beyond the raw integer 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: runs JavaScript inside Studio One's script engine and returns the result. This is unmistakably distinct from all sibling live_* tools (transport, markers, tracks, etc.), which perform fixed DAW operations rather than arbitrary scripting.

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 a clear prerequisite ('Only works when the bridge was installed with --allow-eval') and a concrete use case ('exploring the undocumented object model') with an example call. It does not name alternatives for the cases where eval is unavailable, 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.