set_watch

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, openWorldHint=false), and the description adds genuinely new behavioral context: a 409 signals that a manual recording owns the watch loop, and a first start on a fresh install can trigger a macOS microphone/screen-recording prompt requiring interactive grant. These are exactly the failure modes an agent cannot infer from the structured fields.

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 tight sentences, front-loaded with the core action and followed by error and permission context in priority order. 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?

No output schema exists, but for a one-parameter toggle the description covers the operation, the key error case, and the external permission prerequisite. Nothing an agent needs to invoke it correctly is missing.

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 100% and the single 'action' enum is richly documented in the schema itself (including why toggle is omitted). The description adds nothing beyond that, so the baseline 3 applies.

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 (start/stop) and resource (automatic meeting detection / watch loop), and anchors it to a concrete UI equivalent ('the same thing the menu bar's Start Watching item does'). An agent can separate this from get_watch_status (read-only status) without opening either 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 clear context for invocation (start vs stop, the 409 conflict case, and the interactive-permission prerequisite before relying on it). It does not explicitly route to a sibling alternative such as get_watch_status for checking state first, so it stops short of full when/when-not guidance.

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