grok_agent_consult

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

With no annotations, the description carries the burden of behavioral disclosure. It does disclose two important traits: the session is 'isolated' and 'read-only.' However, it does not explain whether the session is asynchronous, what resources are created, how results are obtained, or any side effects beyond being read-only. This is partial transparency but leaves significant behavioral gaps.

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 a single, front-loaded sentence with no redundant or filler content. Every phrase adds distinct semantic value: 'Start', 'isolated', 'read-only', 'consult session', and the non-git root support. It is highly concise and well-structured.

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?

This is a complex tool with 3 top-level parameters, a nested task object containing 15 properties, no annotations, and no output schema. The description provides no context about how the consult session works, how to construct the task packet, what the response contains, or how it relates to sibling tools. This is far from complete 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 description coverage is 0%, and the description provides no parameter-level meaning. The tool has a complex nested 'task' object with many required fields, yet the description does not explain 'task', 'lane', 'transport', or any subfields. The phrase 'allowlisted roots' vaguely hints at project_root but fails to compensate for the complete lack of parameter documentation.

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 states a specific action ('Start an isolated read-only consult session') and clearly identifies the resource (consult session). The 'read-only' qualifier distinguishes it from sibling execute/fix tools, and 'consult' aligns with the role enum. Although 'non-git exact allowlisted roots' is jargon, the core purpose is unambiguous.

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 gives no guidance on when to use this tool versus alternatives. It implies a read-only consult context but does not state explicit use cases, exclusions, or mention sibling tools like grok_agent_execute or grok_agent_fix. 'Non-git exact allowlisted roots are supported' is a capability note, not usage guidance.

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