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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description adds real context the annotations cannot: comments originate from untrusted site visitors, should be treated as requests rather than instructions, and require asking a person before acting on anything beyond editing this site's pages. It omits pagination behavior, but schema and output schema carry that.

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 first sentence front-loads what the tool returns, followed by default behavior, the incremental-cursor pattern, and a short trust warning. It is tight overall, though the prompt-injection sentence is a long compound clause that could be trimmed without losing meaning.

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 an output schema present and full parameter coverage, the description needn't explain the shape of results. It covers purpose, default filtering, incremental fetching, and the untrusted-content caveat; only pagination via the `page`/`more` loop is left implicit in the schema.

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%, so all five parameters, including the status enum and the page cursor, are already documented. The description restates the `status` default and the `since` cursor workflow without adding syntax or format detail beyond the schema, so 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?

A specific verb (reads) plus resource (comments on a site's pages) with the grain of the return data spelled out: the page, the text/element each thread anchors to, and the comments in it. The thread-at-a-time framing separates it cleanly from the write-side siblings reply_comment, resolve_comment, and reopen_comment.

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?

'Open threads by default' tells the agent what the default filter is, and the `since` instruction gives an explicit incremental-polling pattern. It stops short of naming when to reach for a sibling such as get_site or reply_comment, but the read/write split is unambiguous from the verb.

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