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

Goes well beyond the annotations by disclosing partial-success semantics (invalid[] and alreadyWatched[] arrays), the 500-registration capacity ceiling, and the auth requirement (OAuth or account key, not a system key). The additive behavior is consistent with destructiveHint=false and idempotentHint=true, so there is no annotation contradiction. It stops short of describing ordering or exactly how many succeed per call.

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?

Front-loads the core semantic (additive, unlike jt_watch_set) and then layers failure modes, capacity, and auth in three compact clauses with no filler. The heavy parenthetical and dense punctuation make it slightly harder to scan than an ideal definition, but every sentence 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?

Covers the sibling distinction, the mutation's additive scope, auth prerequisites, capacity limits, and partial-failure outcomes, even though an output schema exists to document the return arrays. Nothing an agent needs in order to call this 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 coverage is 100% and the single parameter's format notes (hyphen-optional, any case) live in the schema already. The description only reinforces the parameter indirectly via the 500-item cap, which mirrors maxItems. Baseline 3 is appropriate when the schema carries the parameter detail.

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 ("add registration(s) to this account's watch list") and immediately distinguishes itself from jt_watch_set, the sibling that replaces the whole list. An agent can route between the two 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?

Explicitly names the alternative (jt_watch_set) and the condition that selects this tool over it: additive vs. whole-list replacement. It also states the account-connection prerequisite, so preconditions are covered rather than left to inference.

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