execute

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

With no annotations at all, the description carries the full burden, and it does disclose one important behavior: execution happens on a dedicated branch in a separate worktree, so the main working tree is untouched. It says nothing about whether the call is long-running/blocking, what permissions or auth it needs, what happens on failure, or that it spawns an external coding agent process.

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?

One sentence, front-loaded with the action and immediately followed by the branch/worktree constraint. Nothing is redundant or padded.

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?

For a tool that spawns an agent in a new worktree with six parameters, no annotations, and no output schema, a single sentence leaves major gaps: agent/model/effort semantics, whether execution is synchronous, and how results or failures are surfaced. The vocabulary (run_id, worktree, agent enum) is also undefined for a caller unfamiliar with the system.

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 only 33% (only 'verify' and 'session' are documented in the schema), so the description should compensate, and it does not mention any parameter. In particular plan_id, agent, model, and effort — including that agent constrains which CLI backend runs — are left entirely unexplained.

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 gives a specific verb ('Implement') and object ('a finished plan'), plus concrete detail about the target branch (kraken/<run_id>) and isolation (separate worktree). It does not, however, distinguish this from siblings like 'run' or 'chain', which an agent could easily confuse with it.

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?

'A finished plan' implicitly signals the precondition that a plan must already exist and be complete, which hints at when to use it. But there is no explicit when-not guidance, no mention of 'plan' or 'resume' as the prerequisite/alternative steps, and no note on whether it can be re-invoked after a cancel.

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