Sort comments and draft replies

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds meaningful behavior beyond that: it clarifies that drafts are generated but never sent, that each comment receives a priority, a suggested action among reply/private reply/hide/delete, and that without an AI model only the raw comments are returned. It does not cover cost/latency of AI processing, but the side-effect profile and degraded mode are well disclosed.

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 core action and its outputs are front-loaded, and the important safety fact ('nothing is sent') is stated in a short standalone sentence. The taxonomy list and fallback clause add length but each carries actionable detail.

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 six-parameter, no-output-schema tool, the description does the heavy lifting by enumerating what comes back (categories, priority, suggested action, draft reply, post ideas) and the no-AI fallback. The remaining omission is guidance on the undocumented parameters, which is a modest gap rather than a blocking one.

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?

With 50% schema description coverage, the description partly compensates by explaining the media_id-vs-posts tradeoff ('one post, or the latest posts') and the voice-following role of template. It says nothing about max_comments or unanswered_only, both of which are undocumented in the schema, leaving real gaps.

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 concrete verb and resource (reads recent comments) plus the scope variants (one post, or the latest posts), and names the exact taxonomy it sorts into. It is clearly distinguishable from siblings like list_comments (raw listing) and reply_to_comment (actual sending).

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?

It implies the right context via 'Drafts only: nothing is sent' and describes a no-AI fallback, which hints at when the tool is and isn't useful. However, it never explicitly tells the agent to prefer list_comments for a plain listing or reply_to_comment to actually send a draft, so the routing to alternatives is left to inference.

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