List comments

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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, so the description only needs to add operational detail — and it does: ordering ('newest first') and the returned sub-fields including hidden state. Pagination via cursor is left to the schema rather than described.

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 tight sentences: the first defines the operation and what's returned, the second gives the ID-flow prerequisites. No filler, and the core purpose is front-loaded.

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 rich annotations, no output schema, and only four params, the description covers what the tool does, what the result contains, and how to get/use IDs. The main residual gap is pagination and page-size guidance.

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 50%: 'after' and 'response_format' are documented in the schema, while media_id and limit are not. The description compensates for media_id by pointing at ig_list_media as the source, but says nothing about the limit cap or page-size behavior, so compensation is only partial.

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 on one of the account's posts') plus scope details: newest-first ordering and included fields (replies, likes, hidden state). This clearly distinguishes it from mutation siblings like ig_reply_to_comment or ig_hide_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?

Explicitly names the downstream consumers of the returned comment IDs (ig_reply_to_comment, ig_hide_comment, ig_delete_comment) and the upstream source of media_id (ig_list_media). That's solid routing, though it doesn't state when to prefer this over e.g. ig_get_media for inspecting a post.

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