set_asr

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

With no annotations, the description carries the load and does disclose the key side effect: the choice persists to .witness/config.json. It also characterizes each engine's tradeoff. It stops short of saying whether an unavailable engine errors out or when the change takes effect relative to a running recording.

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 sentences, both dense with decision-relevant content: the scope/persistence clause first, then a compact engine glossary. No filler.

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 single-parameter, no-output-schema tool this is nearly sufficient: it covers effect scope, persistence, and option tradeoffs. The unexplained "auto" value and the absence of any failure-mode note are the only remaining holes.

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 0%, so the description must supply meaning, and it does explain four of the five enum values with useful tradeoffs. The fifth value, "auto", is never defined, leaving the agent guessing on a valid and likely common input.

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?

Names a specific verb and resource ("Switch the live ASR engine") and bounds the scope precisely with "for FUTURE recordings", which immediately separates it from the read-side sibling get_asr.

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 "FUTURE recordings" qualifier tells the agent exactly when this applies and implicitly when it does not (it won't change an in-progress session's engine). No explicit pointer to get_asr for reading the current value, but the set-vs-get split is self-evident from the name.

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