run_script

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 the return channel (script return value plus ShowConsoleMsg output), the execution model (single-pass, no defer), the hard stop at timeout_seconds (default 30), atomicity (all project changes in one undo block), and the gating/auth requirement via bridge_config.json. These are non-obvious traits an agent could not infer from the schema.

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-loaded with the core capability and the code/path choice, then constraints in decreasing order of importance. Slightly dense — the final setup-command clause is useful but reads like an appendix — yet no sentence is 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?

Covers the information most likely to cause a failed or surprising call: execution limits, output capture, undo behavior, and the enablement flag, despite having no annotations and no output schema. Minor gaps remain — whether code and path are mutually exclusive and what a failure reply looks like — but the critical unknowns are addressed.

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?

At only 40% schema coverage, the description compensates for the undocumented parameters: it explains `code` as source text, `path` as a .lua file with a defined resolution order (daemon folder, then REAPER's Scripts folder), and supplies the default for the otherwise bare `timeout_seconds`. `args` is left entirely to the schema, which does document it, so the description stays above baseline without being exhaustive.

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 ('Run Lua inside REAPER with the full ReaScript API') and immediately disambiguates the two invocation modes (inline `code` vs `path` to a .lua file). An agent can distinguish this from action-based siblings like run_action or raw_command without opening the schema.

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 concrete operating preconditions — the tool is 'Off until allow_script_execution is true' with the exact install flag to enable it — and states a hard constraint (reaper.defer unavailable, script must finish in one pass). It does not name alternatives such as run_action or raw_command for cases where a canned action would suffice, so routing guidance is implied rather than explicit.

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