ads_client_profile_batch_send

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

With no annotations, the description carries the full burden and does it: Telegram Premium requirement, a non-blocking read-only unread-human-dialog preflight, a blocking activity preflight (stale exact last-seen, hidden profiles without an avatar), 15-second minimum spacing, opted_out blocking, stop-on-first-error, and per-message recording of successful sends. These are exactly the operational traits an agent cannot infer from the schema.

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 action and scope, and nearly every clause contributes a distinct operational fact. It is a dense multi-clause run-on, though, which makes the blocking preflight rules harder to parse than a short bulleted structure would.

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 destructive batch-send tool with no annotations and no output schema, the description covers prerequisites, preflights, rate limiting, and partial-failure behavior (stops on first error, records successes). It does not describe what the caller gets back (sent/failed counts, per-profile results) or whether re-running after a mid-batch failure is safe, which is a meaningful gap for a batch mutation.

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 80%, so the baseline is 3, but the description adds real meaning: it names the two draft_key values, ties the activity preflight to the last-seen window (max_inactive_days), and restates the 15-second floor that min_delay_seconds enforces. Only profile_ids and the exact stale-last-seen threshold semantics remain underexplained.

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 (send), a specific resource (a saved client-profile draft, firstContact or replyToUnread), and a bounded scope (up to 50 active profiles, one batch confirmation). This clearly separates it from sibling single-message tools like ads_client_profile_message_add or ads_telegram_account_send.

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 a hard precondition (the exact saved draft and every variation must have been approved; any change requires fresh approval) and the confirmation requirement, so the agent knows when the tool is legal to call. It never names an alternative sibling or says explicitly when not to use this versus a single-recipient send, so it stops short of a 5.

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