ai_inbox

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

With no annotations, the description carries the behavioral disclosure burden. It does state that the tool is a queue meant to be answered by the agent and that it should be polled each turn, which is useful. However, it does not disclose whether polling consumes items, what side effects occur, or how 'unanswered' is determined.

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 description is extremely short but every phrase earns its place: it defines the resource, connects it to the agent's task, and gives explicit polling cadence. There is no redundancy or filler.

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 simple poll tool with two optional parameters and no output schema, the description gives enough to understand the high-level purpose and invocation cadence. However, it omits the expected return shape and the semantics of onlyUnanswered, which an agent would benefit from knowing before calling.

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%, and the description adds no information about limit or onlyUnanswered. The parameter names are somewhat self-explanatory, but the description fails to compensate for the schema gap, especially the meaning and default behavior of onlyUnanswered.

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 clearly identifies the tool as a pollable queue of WhatsApp prompts waiting for the agent to answer. The verb 'Poll' plus the resource 'antrean prompt /Wa.p' makes the core action explicit, and it distinguishes this from sibling tools like list_messages or ai_reply.

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 instruction 'Poll ini tiap giliran' explicitly tells the agent when to use this tool: every turn. It does not explicitly state when not to use it or name alternatives, but for a polling tool the cadence guidance is strong and actionable.

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