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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds substantial behavior beyond them: page size and ceiling, cursor chaining via `next_cursor`, the fact that newest comments sit on the final page, and that deleted comments remain in the listing with empty bodies but intact replies. That last point in particular would be surprising and wrong to infer from annotations alone.

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 the essential ordering and pagination rules before the field-level detail, and nearly every clause earns its place. The single dense paragraph makes the frontmatter semantics harder to scan than a short bulleted breakdown would, which keeps it off a 5.

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 carries the full burden of explaining return values and does so thoroughly: `frontmatter.seq`, `reply_to` vs `in_reply_to` for one-level thread grouping, `version` for downstream edits, `updated_at`/`updated_by`, and the deleted-comment representation. An agent can read and reconstruct threads correctly from this alone.

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 75% and already documents `cursor` and the issue/project key formats, so the baseline is 3. The description goes beyond by linking the output `next_cursor` to the input `cursor` and by restating the 50-default / 200-max pagination contract, which makes the two undocumented-ish parameters unambiguous in practice.

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 (list comments) plus the scope and ordering (for one issue, oldest first). It is immediately distinguishable from the comment-mutating siblings add_comment, update_comment, delete_comment, and from get_issue / get_issue_context.

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?

Gives concrete operational guidance: 50 per page, limit up to 200, page until `next_cursor` is absent, and the non-obvious warning that the newest comment is on the LAST page. It also tells the agent to skip `deleted: true` entries when reading a thread and points to update_comment/delete_comment for the version field. It does not explicitly name a sibling alternative to use instead in any condition, so it falls short of a 5.

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