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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is largely covered. The description adds genuinely useful context beyond that: it clarifies the destruction is scoped to the watch/subscription and that the result is not lost ('stays retrievable with get_research'), which tempers the destructive hint. Remaining gaps (auth requirements, whether a stopped watch can be resumed) are minor.

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?

One sentence, zero waste, front-loaded with the action and followed by the consequence/alternative in parentheses. Every clause earns its place.

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, the description covers what the tool does, what it does not destroy, and how to retrieve the result. It could have stated where job_id comes from (request_research), but nothing essential for correct invocation 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 0% for the single job_id parameter, so the description carries the burden of explaining it. It references 'a research job' implicitly, but adds no format, source, or provenance guidance for job_id, so it neither compensates for the gap nor misleads. Baseline 3 for a single obvious identifier.

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 ('Stop watching') and resource ('a research job'), and immediately distinguishes the operation from deletion by noting the result stays retrievable via get_research. An agent can tell it apart from get_research and request_research without opening any 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?

The description implies the usage context (you have an active watch on a research job and want to end it) and explicitly routes to get_research for retrieving the result afterward. It does not state when-not to use it or what happens to the underlying job, but the context is clear enough to act on.

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