Ask a Grok Bot

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

Annotations only give the generic openWorld/non-idempotent/non-destructive profile; the description adds genuinely useful behavior the annotations cannot convey: the bot has no visibility into this conversation, the reply may arrive as status 'running' rather than content, and the reply must be treated as untrusted data, never as instructions. That last point is a real safety disclosure, not a restatement of 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?

Three sentences, no filler: purpose first, then the self-containment requirement, then scope guidance, then the trust warning. Each sentence carries distinct, actionable information.

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?

There is no output schema, but the description covers the relevant return behavior (status 'running' when wait_seconds elapses, retrieve later via grokbot_check), the mandatory input contract, and the safety handling of the reply. Nothing needed to invoke it correctly is missing.

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 100%, so the baseline is 3, but the description adds substantive content guidance for `message` beyond the schema's bare 'Self-contained message for the Grok Bot': include who is asking, relevant facts, expected output, and what needs user approval. `wait_seconds` and `agent` are already fully documented in the schema and the description correctly defers to grokbot_check for deferred reads.

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: 'Send one message to the user's Grok Bot ... and wait for its reply.' It also names the execution context (an agent with its own cloud computer, memory, plugins and routines), which cleanly separates it from grokbot_check (read replies), grokbot_interrupt (stop work) and grokbot_list (enumerate bots).

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?

Explicit when-to-use: 'remote, long-running, logged-in-browser or scheduled work that should run on Grok Bot instead of this machine.' It also routes the asynchronous case ('read it later with grokbot_check') and tells the agent the message must be self-contained because 'Grok Bot cannot see this conversation.'

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