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

Beyond the annotations (readOnlyHint false, idempotentHint true), the description discloses how invalid registrations are handled ('come back in invalid[]'), how duplicates are handled ('already-watched ones come back in alreadyWatched[]'), the max capacity, and the authentication requirement. These are behavioral details not present in the structured annotations, and nothing contradicts them.

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 sentences, front-loaded with the primary purpose and the key contrast with jt_watch_set. Every sentence contributes essential information: the action, the distinction, behavior on edge cases, the limit, and the access requirement. No fluff.

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?

Given the single-parameter schema, existing annotations, and likely output schema, the description covers the essential context an agent needs to call the tool correctly: what it does, how it differs from jt_watch_set, edge-case behavior, capacity limits, and authorization. The presence of an output schema means return details don't need to be repeated.

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?

The input schema fully describes the 'registrations' parameter (format, case, hyphen, length). The description adds value by explaining what happens with invalid or duplicate entries, which directly informs how to interpret parameter results. This goes beyond the schema's static type description, though the core parameter semantics are already covered.

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?

The description clearly states the action: 'Add registration(s) to this account's watch list' and explicitly distinguishes from jt_watch_set by noting it does so 'WITHOUT touching the rest'. The verb-resource pair is specific and the sibling contrast removes ambiguity about which watch-modifying tool to choose.

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?

It explicitly names jt_watch_set as the alternative that replaces the whole list, implying this tool should be used when only adding to the existing list. It also states a prerequisite ('Requires an account key (Enterprise)') and the total limit of 500 watched registrations, giving clear guidance on when this tool applies and its constraints.

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