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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description doesn't need to restate it. Instead it adds genuinely non-obvious behavior: include_own is hidden by default 'because they need no action', spam rows are hidden by default, and unseen_only uses a last_seen_at >= last_message_at comparison. It also spells out the pagination protocol (offset += returned count), which is exactly the kind of operational detail annotations cannot convey.

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 purpose and return shape, then filters, then pagination mechanics, then the sibling hand-off — a logical order an agent can scan. It is dense but somewhat long, with a few clauses that duplicate what the schema already documents verbatim (limit/offset, q, sort).

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 13-parameter tool with no output schema, the description compensates by enumerating the returned fields (id, platform, thread kind, participant, unread/like counts, spam/seen state, preview) so an agent knows what it will get back. Combined with default-hiding behavior and pagination guidance, nothing essential for a correct first call is missing.

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; the description earns extra by explaining intent behind defaults rather than just restating them — e.g. why own top-level threads are suppressed and what 'unanswered' means in workflow terms. It remains largely a prose mirror of the schema for filters like platform and sort, which keeps it from a 5.

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?

Opens with a specific verb and resource ('Lists inbox conversation threads') and immediately scopes what a thread is (post/video comments and DMs) plus the ordering ('most recently active first'). It distinguishes itself from get_conversation_messages by describing a filtered, paginated listing rather than a thread read, and enumerates the returned fields so an agent knows what the row contains.

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 states the downstream use case: 'Use this to find a conversation_id before calling reply_to_comment, like_conversation, mark_conversations_seen, or mark_conversations_spam.' That is a strong when-to-use signal tied to real siblings. It stops short of naming when NOT to use it (e.g., use get_conversation_messages to read a thread's contents), so a 4 rather than a 5.

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