Execute in worktree

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

Annotations already declare destructiveHint=false, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety and side-effect profile is covered. The description adds two genuinely useful facts beyond that: execution happens in an isolated git worktree, and completion requires a real diff plus the requested evidence. It omits auth/permission needs (the task's permission_profile enum hints at this), concurrency behavior, and that each call spawns a fresh non-idempotent run.

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?

Two short sentences, front-loaded with the core action. Nothing is padded, though the second sentence is telegraphic and its referent ('completed', 'requested evidence') is unclear without prior knowledge of the task packet.

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 high-complexity tool: a nested required task packet with 20 fields, no output schema, and no schema-level descriptions anywhere. A two-sentence description leaves an agent guessing about required packet contents, lane/transport semantics, and what a successful invocation returns.

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% across three parameters, and the nested task object carries ~20 undocumented fields (objective, expected_artifacts, test_commands, acceptance_criteria, permission_profile, etc.). The description explains none of them, so it fails to compensate for the coverage gap; the only faint signal is 'requested evidence', which loosely gestures at expected_artifacts.

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 concrete verb and resource: 'Start workspace execution in a git worktree'. An agent can tell this launches a run rather than merely polling or reviewing. However, it does nothing to distinguish itself from the many sibling start/execute tools (grok_agent_start, grok_delegate_start, grok_agent_consult), so the sibling-differentiation criterion for a 5 is unmet.

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?

There is no when-to-use guidance, no prerequisites, and no named alternative among the ~24 siblings. The trailing clause about 'completed' describes an outcome condition, not when an agent should pick this tool over grok_agent_start or grok_delegate_start.

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