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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes beyond them usefully: it explains that watchers are email recipients, that only users who can still open the project appear, and that watching is personal state with no version and no appearance in history or the md file. It stops short of describing the shape of the returned entries.

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?

The content is useful but redundant: the opening line repeats the tool title verbatim including '(spec D92)', and the notion of 'who gets emails besides its assignee and reporter' is stated twice. The '(spec D92)' reference consumes the highest-attention position without helping an agent decide anything.

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?

There is no output schema, so the description must carry the return semantics, and it does: it says a list of people is returned, applies a visibility filter, and notes the `watching` flag for the token's own user. It does not say what fields identify each watcher (name, id, email), which is the remaining gap.

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 both issue_key and project_key are documented with patterns and examples in the schema itself. The description adds nothing about either parameter, 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?

The description concretely states what the tool returns: the set of people who receive this issue's status-change/comment emails, with 'only people who can still open the project are listed' pinning down the filtering rule. The verb 'list' is never used, so the retrieval framing has to be inferred from the 'who watches' phrasing, and the closely related siblings watch_issue/unwatch_issue are never contrasted.

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?

Usage is only implied: an agent can infer it should call this when it needs to know who gets notified about an issue. There is no explicit when-to-use statement, no exclusions, and no pointer to watch_issue/unwatch_issue, which are the obvious neighbouring operations in the sibling list.

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