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

With no annotations, the description carries the full burden and does so: per-user read state ('a colleague reading the same shared mailbox keeps their own'), the re-bolding behavior on new mail ('A message arriving after this call turns the thread bold again'), and precise batch failure semantics including per-thread isolation and the 'error only when none succeeded' rule.

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 the core semantic (clears bold, for you) before the get_conversation disambiguation and batch detail, so an agent gets the gist in the first clause. It is a dense single paragraph and the quoted token names add some bulk, but nearly every clause carries a distinct behavioral fact.

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?

No output schema exists, yet the description explains the shape of the batch response and the aggregate error condition, so nothing an agent needs to interpret results is missing. Combined with the per-user scoping and re-bold behavior, the definition is complete for a single-parameter mutation tool.

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% and the single parameter's description already covers the string-or-list forms and the 50-item cap. The description still adds batch-specific meaning: order preservation, the 'results' array with per-item 'ok'/'result'/'error', and the 'succeeded'/'failed' counters.

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+resource ('Clears the bold on a thread') and immediately scopes it as per-user ('for YOU'), which distinguishes it from mailbox-wide or fetch-style siblings. It also explicitly separates itself from get_conversation, so an agent can pick correctly without reading either schema.

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 an explicit when-not ('Reading a thread with get_conversation does not do this by itself, on purpose') and an explicit bulk-usage rule ('give conversation_id the list of their ids, in ONE call rather than one call per thread'). The condition selecting each mode is stated, not inferred.

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