rew_command

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the warning bar is pre-set; the description adds useful context by revealing the tool is a broad dispatcher spanning save/load and measurement processing, which is why it can mutate state. It still does not say what can be destroyed, whether execution is synchronous, or what happens on an invalid command, and "sweeps (Pro)" is the only capability caveat offered.

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?

Three sentences, front-loaded with the action and no filler; the scope list is dense but earns its place by signaling breadth. It could be tightened by folding the discovery prerequisite into an explicit tool reference rather than a standalone imperative.

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?

This is a destructive, wide-open dispatcher with 7 undocumented parameters and no output schema, so the description should carry most of the load and it does not. An agent still cannot tell how to format `parameters`, what `wait` does, or how `progress_path`/`commands_path` differ from `path`.

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% across 7 parameters, so the description must carry the burden and it largely does not. The endpoint mention loosely maps to `path` and the discovery sentence loosely maps to `command`/`parameters`, but `wait`, `wait_timeout` (capped at 600), `commands_path`, and `progress_path` are given no meaning anywhere.

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 pairs a concrete verb and resource ("Run a REW command at a /command endpoint") and enumerates the command scopes it covers (generator, sweeps, EQ, alignment, RTA, measurement processing, save/load). That distinguishes it from narrower siblings like rew_analyze_measurement or rew_export_measurement, though it never names rew_request or rew_call_api, which look like the nearest analogues.

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?

"Discover command choices and parameters first" supplies a real prerequisite and implies a describe/search step must precede invocation, which is useful sequencing guidance. However, it does not name the sibling tool that performs that discovery (rew_describe_api / rew_search_api are present in the catalog) and gives no when-not-to-use guidance versus rew_request or rew_batch.

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