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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior. The description adds two genuinely new hints: 'as far as the platform shows them' signals that results may be incomplete or truncated, and 'Counts as browsing' implies a quota or rate-limit cost. Both are useful but left vague and unexplained.

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 sentences with the resource and author scope front-loaded and no filler. The second sentence is cryptic rather than wasteful, so it does not hurt structure much.

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?

For a four-parameter, paginated, open-world read tool with no output schema, the description is minimally adequate. It never explains pagination via cursor, what the returned comment objects contain, or how the platform-coverage caveat manifests, leaving real gaps.

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 75%, with limit, cursor, and user_id already documented in the schema; account_id is undocumented in both places. The description adds no meaning beyond the schema, so the baseline of 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?

The description names the resource (comments) and scopes it to a specific author ('written by a person'), which separates it from a general comments listing like list_comments. It implies a list operation without stating the verb explicitly and never names the sibling it differs from, so it falls short of a 5.

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?

'Counts as browsing' gestures at consumption behavior but gives no actual when-to-use guidance, no prerequisites, and no comparison against list_comments or other comment-related siblings. An agent must infer the selection criteria entirely.

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