ads_telegram_public_reply_upsert

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

With no annotations, the description carries the full burden, and the 'never sends or marks messages read' clause usefully rules out the wrong assumption that this is a messaging tool. However, for a 21-parameter mutation it omits what an upsert actually destroys (does re-saving overwrite status/decision_note on an existing row?) and what identity key triggers the update-vs-insert.

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 front-loaded clauses with no filler, and the local-only constraint is placed where it will be read before invocation. Slightly too terse for the surface area, but every sentence earns its place.

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?

A 21-parameter, nested, mutation-style tool with no annotations, no output schema, and zero schema descriptions is given only two sentences. Given that complexity, the definition leaves far too much undefined for an agent to call it correctly or predict its effect.

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 0% across 21 parameters, so the description needed to compensate and instead names none of them. Critical semantics — which combination of telegram_chat_id/telegram_message_id/public_url identifies the record for upsert, what the status enum states mean, and what relation_type 'reply' vs 'mention' changes — are left entirely undocumented.

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 ('Save or update' / upsert) and a specific resource ('one public Telegram reply/mention found under a message from the connected account'), which is enough to separate it from the read-oriented siblings ads_telegram_public_reply_list and _sync. It does not name those siblings explicitly, so differentiation is inferential rather than stated.

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?

There is no statement of when to use this versus ads_telegram_public_reply_sync, _list, or _status — the agent must infer that this is the persistence step after discovery. 'Local-only; never sends' clarifies safety but not selection criteria or prerequisites.

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