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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description adds genuinely new context: the exact return shape ({ app_id, expires_at }), the meaning of null values when the conversation is idle, and the platform restriction. The phrase 'refresh the chat's metadata.thread_control' sits in mild tension with readOnlyHint since it implies a state update, but it reads as a cache/state refresh rather than a true contradiction.

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 platform restriction is front-loaded, followed by purpose and then return semantics — a sensible ordering with no filler. The trailing app-ID constants are dense but genuinely useful for interpreting returned values.

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 no output schema, the description takes on the burden of explaining return values and does so precisely, including the null/idle case. Combined with the platform restriction and annotations covering safety, an agent has everything needed to call and interpret this 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?

There is a single parameter with 100% schema description coverage ('Chat hashid OR external_conversation_id of a Facebook or Instagram chat'), so the schema carries the semantics. The description adds no further detail about the chat_id format, which is the baseline 3 case.

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?

The description names a concrete verb and resource in plain language ('Ask Meta which app controls a conversation right now'), which is more informative than the tool name alone. It is distinguishable from the dm_chat_thread_control_{request,take,pass,release} siblings by framing itself as a query, though it never names those siblings explicitly.

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?

The 'Facebook & Instagram only' scope restriction is a useful usage gate, and the note that both fields are null when the conversation is idle hints at an appropriate call condition. However, it never states when to use this versus the thread_control_take/request/release tools that manipulate the same thread-control state, leaving the primary routing decision to inference.

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