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

Annotations already establish read-only, non-destructive, open-world behavior, so the bar is lower. The description adds context outside the annotations: result ordering (most recent first), the identity of each thread counterpart, unread-state reporting, and the authentication requirement (a Cotlet API key with access to this app).

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 well, but the first sentence largely duplicates the second ('your direct message threads with the other person, last message and unread state' vs 'lists your direct message threads ... with the other person, the last messages and whether the thread is unread'). One of those two sentences could be dropped with no loss.

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 read-only paginated list with no output schema, the description covers ordering, entry contents, the unread filter, follow-up routing, and auth prerequisites. Pagination behavior is only implied through the cursor parameter, which the schema handles, so nothing critical 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 description coverage is 100%, so limit, cursor, and unread_only are already documented in the schema. The description restates unread_only's meaning ('only what needs an answer') without adding syntax, defaults, or range detail beyond the schema, so the baseline 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?

States a specific verb and resource (lists your direct message threads) plus what each entry contains: the other person, the last message, and unread state, ordered most-recent-first. That is concrete and distinct from reading comments or a single thread, though it never explicitly contrasts itself with siblings like soundcloud_list_comments.

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 explicit conditional guidance for the main flag ('Set unread_only to see only what needs an answer') and hands the agent off to the correct follow-up tool ('Pass conversation_id or the person's profile URL to send_message'). There are no explicit when-not-use conditions, but the routing to send_message makes the intended workflow clear.

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