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

Annotations only say readOnly/openWorld, but the description adds non-obvious behavior: non-chronological 'Most relevant' ordering, a truncated first page versus 10-comment subsequent pages, and a data-integrity caveat that likeCount is rounded in abbreviated form ('2.4K') at source. It also discloses the 1-credit cost.

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-loaded with purpose, then pagination, then counters, then caveats — no filler sentences. It is dense and longer than typical, but nearly every clause contributes information an agent needs.

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?

No output schema, so the description carries the return contract and does so adequately (author, reaction count, reply count, ordering, rounding caveat). Only the cache_max_age parameter and exact response envelope remain undocumented.

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?

With 67% schema coverage, the description usefully explains that cursor comes from a previous response's pagination.cursor and that the url must be a post/video/reel. The cache_max_age parameter is left unexplained in both schema and description, a minor gap.

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?

Specific verb+resource (comments on a post) with scope qualifiers: top-level only, public posts, default 'Most relevant' ordering. It also names the sibling tools it is not (facebook_post for the total, facebook_commentReplies for replies), so an agent can discriminate without opening schemas.

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?

Explicit routing: use /v1/facebook/comment-replies for replies under a comment, and /v1/facebook/post for the full comment total. It also states the concrete pagination procedure (pass pagination.cursor back for the next ten after the ~2-comment first page).

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