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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. The description adds useful facts beyond that: results are newest-first and capped at 100, so the agent knows there is no deeper paging. It still says nothing about the response shape beyond member_id or about empty/error cases.

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, front-loaded sentences with no filler; the ordering and cap land before the downstream-tool hint. The opening fragment 'Who liked a post or a comment.' is slightly telegraphic but not wasteful.

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 no output schema, the description compensates partially by naming member_id and how to reuse it, plus ordering and the 100-item ceiling. It stops short of describing the full returned member fields, which is the remaining gap for an agent parsing results.

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 already documents group format, the 1-100 limit range, and that post_id may be a comment_id. The description only restates the post/comment duality, adding no syntax or format detail beyond the schema, 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?

States a specific verb and resource ('lists the members who liked a post or a comment'), and the comment-liking scope is a genuinely useful distinction the name list_post_likes does not convey. It is easily separable from the mutating sibling like_post and from get_post.

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?

Frames the use case as 'the like count under it opens', which tells the agent when to reach for this. It also chains forward by naming send_message and get_member as consumers of member_id, though it never states an explicit alternative or exclusion.

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