ads_telegram_public_reply_sync

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

With no annotations, the description carries the full burden and does much of it: it declares the operation non-mutating toward the platform, states a Premium entitlement requirement, and bounds the read ('bounded recent history', 'small context window'). It leaves unstated what is written on the save side and any rate/size limits beyond the schema's numeric caps.

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?

Two sentences, zero filler: the action and scope come first, the rationale second, and the constraints compressed into one negation clause. Every element does work.

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 annotations and no output schema, so the definition must stand alone, and it covers purpose, safety boundaries, entitlement, and read bounds. The one real gap is the absence of any statement about what the sync returns or how much gets persisted per run.

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 75%, and the description supplies the intent behind the undocumented gaps: chat_refs are 'selected public Telegram chats', limit_per_chat is a bounded 'recent history', and context_messages_after is the 'small context window after each outgoing message'. Only project_id remains unexplained, which is why this isn't 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?

Specific verb pair (read history, save replies) plus a clearly scoped resource (public Telegram chats) and a stated mechanism (context window after each outgoing message). It separates itself from upsert/list/status siblings by describing a read-and-record sync pass, though it never says where the captured replies are persisted.

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 the trigger condition explicitly — people may answer without using the reply action — which tells the agent why this sync exists rather than a plain message search. Negative scope (never sends, joins, collects participants, marks read) rules out the obvious confusions with send/reply/chat_mark_read siblings, but no sibling is named as an alternative.

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