watch

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

Annotations mark this as a non-read-only, non-destructive mutation; the description adds the key behavioral trait that effects are deferred to the next `torus watch run`, which the annotations cannot convey. It omits idempotency (what happens if already watched) and error/duplicate behavior.

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 short sentences, effect stated first, the deferred-run caveat parenthesized in place. 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?

With an output schema present, return values need no explanation, and annotations cover safety, but the description leaves gaps typical of a state-changing tool: behavior on re-watch, the purpose of `note`, and how to reverse the action with unwatch.

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?

Only 50% schema coverage: `entity` is documented in the schema, but `note` is undocumented in both schema and description, and the description never mentions either parameter. With low coverage the description should compensate and does not.

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 ('Watch a company') and describes the concrete effect: new SEC filings become events. It implies its inverse sibling (unwatch) and companion (list_watches) but never names them, so differentiation is only partial.

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?

Adds a genuine usage rule not inferable elsewhere: subjects of open theses are watched automatically, implying you don't need to call this for those entities. No explicit guidance on unwatch/list_watches or when-not to use, keeping it below a 5.

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