grok_agent_update

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

With no annotations, the description carries full responsibility. It discloses the two modes (preview vs. execute), the effect of confirm (pulls and reinstalls), the side effect (asks to restart the MCP host), and the refusal condition (dirty checkout). This is transparent about all behavioral aspects.

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 concise, using clear sentences to cover the purpose, behavior, and conditions. It avoids unnecessary detail while being informative, making it easy to parse.

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?

In the absence of an output schema, the description explains what happens in each mode: preview returns exact steps, confirm performs the update and prompts for restart. It also covers the dirty-checkout edge case, making it complete for an agent to decide and invoke.

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 only parameter, confirm, is described in the schema ('Run the update. Omit to preview it.') and further elaborated in the tool description. The description clarifies that without confirm it returns steps, and with confirm it acts, adding clear semantic meaning.

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 states the tool checks if the running bridge is behind its git remote and updates it. It specifies the action (check and update) and the resource (running bridge), making it distinct from sibling tools like grok_agent_poll or grok_agent_start.

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?

It explains when to use it (to check for updates and apply them) and how to invoke it (with or without confirm). It also notes the refusal condition (dirty checkout). However, it does not explicitly compare to alternative tools, though the context implies this is the update tool. Slight room for improvement.

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