update_whatsapp_ai_rules

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

Annotations already declare non-read-only, open-world, idempotent, non-destructive, so the safety bar is partly met; the description adds real behavioral context beyond that: list-replacement semantics, the per-message decision order, and the fact that the response carries warnings when the saved combination would silence the AI and must be relayed. No contradiction with the annotations.

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-loads what the tool changes, then partial-update mechanics, then decision order, then what it does not do and which tool handles that instead, ending with the response-warning caveat. Dense, no filler, and each sentence carries a distinct instruction.

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 mutation tool with no output schema, yet the description covers replace/merge semantics, ordering of evaluation, sibling routing, and return-side warnings. Combined with the detailed nested schema, an agent has everything needed to call it correctly and interpret side effects.

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?

The nested schema is already richly annotated per field, so the description's added value is mainly the merge/replace distinction and the read-before-write workflow, plus the decision-order framing that ties availability, participantList, thread ownership, triggerPhrases and aiRule together. Some of that (whole-list replacement) is repeated from the schema descriptions, so it is strong but not fully additive.

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 and resource ('Change the WhatsApp "AI rules" of a Convocore agent') plus what those rules govern (when the AI replies to inbound WhatsApp messages). Explicitly names the adjacent capabilities it is not (prompt editing via update_agent/patch_agent_prompt, pausing via update_whatsapp_number_settings aiPaused), so it is distinguishable from siblings without opening a 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 concrete when-to-use guidance ('partial update: send only the fields to change'), a critical precondition ('read them first with get_whatsapp_ai_rules to add or remove one entry'), and explicit exclusions with the correct alternative tool named for each. Nothing about routing between siblings is left to inference.

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