pi_execute

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

With no annotations, the description carries the full disclosure burden. It does add genuine value by stating the task runs in a disposable worktree or file-copy sandbox and returns a job_id, so the agent knows the operation is isolated and asynchronous. However, it says nothing about permission requirements, what the escalation flags (allow_bash, allow_unscoped) unlock, the 5-file cap, failure behavior, or whether the sandbox is cleaned up — critical gaps for an unannotated write tool.

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 sentences, front-loaded with the action and sandbox model, then the return/next-step contract. Nothing is padded. It is slightly under-sized for a 12-parameter tool, but no sentence is wasted.

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 with 12 parameters, 0% schema coverage, no annotations, and no output schema, the description leaves too much unexplained. The verify_command/success_criteria contract and the allow_bash/allow_unscoped escalation semantics are the crux of safe invocation and are entirely absent.

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 12 parameters, so the description must compensate and largely does not. "Declared-file copy sandbox" faintly maps to the files parameter and "scoped" to allow_unscoped, but required fields like success_criteria and verify_command, plus model, endpoint, thinking, host, base, cwd, and allow_bash, receive no explanation at all.

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 uses a specific verb ("Launch") and a precisely scoped resource: a write task confined to a disposable git worktree or a declared-file copy sandbox. That is far more informative than the bare name, and the job_id/result framing distinguishes it from a synchronous read tool. It stops short of naming which sibling consumes the job_id, so the differentiation is implied rather than explicit.

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 second sentence conveys an asynchronous workflow: launch, then wait and inspect the result. That implicitly routes the agent toward the wait/result siblings, but no alternative is named and no when-not condition is given (e.g., when to use pi_research instead of a write task). Usage is inferable but not stated.

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