Run Grok Build

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

The description discloses that the run is headless and returns metadata, which are behavioral traits not covered by annotations (no destructiveHint, no readOnlyHint specifics). It adds context about permission capping and rejection. The annotations already indicate a non-read-only, non-idempotent operation, and the description expands on that by detailing the permission model and return structure.

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—only three sentences—and front-loaded with the core action. Every sentence adds meaningful information: what it does, what it returns, and how permissions work. No fluff or repetition of schema details.

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?

Given that there is no output schema, the description does cover the key output ('model text plus session, usage, and cost metadata'). The tool is complex with 20 parameters, but the schema itself provides detailed descriptions for each. The description could be slightly more complete by mentioning that the tool runs in headless mode only (which is already clear), but overall it is adequate for an agent to invoke it correctly.

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 100%, meaning every parameter is described in the schema. The description adds value by explaining the overall return structure and permission behavior, but does not add unique semantic context for individual parameters beyond what the schema already provides. A score of 4 is justified because the schema already does the heavy lifting with detailed descriptions and examples (e.g., deny/allow rules in `ToolPrefix(glob)` form).

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 action ('Run a headless Grok Build agent'), the command used (`grok -p`), and the output ('model text plus session, usage, and cost metadata'). It also distinguishes from sibling tools by mentioning headless execution and returning metadata, which is distinct from tools like `status` or `stop` that deal with run management.

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 description mentions permission ceiling ('GROK_MCP_PERMISSION_CEILING') and behavior for exceeded requests ('rejected rather than silently downgraded'), which helps agents understand constraints. However, it does not provide explicit guidance on when to use this tool versus siblings like `review` or `websearch`, or when not to use it.

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