list_comments

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

Annotations already establish a safe read (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: automation comments are collapsed to one-line summaries by default, the compact view omits named fields, unknown after IDs are refused, and invalid/empty order values are refused rather than silently coerced. The UTC-to-the-minute timestamp detail and exclusive-delta pagination behavior are exactly the traits an agent cannot get from structured fields.

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?

Dense but every clause carries information: defaults, compact-vs-full behavior, the after delta semantics, and the ordering guidance. Front-loaded with the most important fact (newest first, default limit 10) and no filler sentences.

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 by describing the compact and full return shapes, default truncation of automation bodies, and pagination via page/limit. Refusal behaviors and ordering defaults are covered, leaving nothing critical for correct invocation unspecified.

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%, so the baseline is 3, but the description adds meaning the schema does not: it enumerates the compact field set (id, author_name, created_at, full body) serving as a stand-in for the absent output schema, and clarifies that after accepts either a UUID or RFC3339 timestamp with exclusive, paginated semantics. This goes beyond restating the schema.

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) with the default ordering and page size front-loaded, so an agent immediately knows what it returns. It never names the near-sibling list_doc_comments, so the task-scoped vs doc-scoped distinction must be inferred from the required task_id parameter alone.

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 clear conditions for option selection: order=asc for chronological reading, include_auto=true to restore automation bodies, full=true for complete REST fields, after= for delta reads. It offers no explicit when-not-to-use or sibling alternatives (e.g., list_doc_comments), so routing guidance is one-directional.

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