plan_run_parallel

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

With no annotations provided, the description carries the full behavioral burden. It discloses the core trait of parallel execution in isolated worktrees/branches, which is valuable. However, it does not mention side effects, cleanup behavior, how results are returned, or error handling, leaving 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 compact and front-loads the most important behavioral information: parallel execution, isolation, and independence. Every sentence contributes: the main verb and resource, the use case with examples, and the relationship to plan_run.

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 fairly complex tool with nested task objects, multiple settings, and no output schema or annotations. The description covers the high-level purpose but omits important context such as return behavior, job tracking, failure handling, cleanup of worktrees/branches, and how to interpret results. An agent would likely need additional exploration or documentation to use it reliably.

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 67%, and the description adds useful context by indicating that each task entry is like a plan_run. It does not meaningfully expand on the wait or timeout_seconds parameters, which are already partially self-explanatory and documented in the schema. Overall, the description adds some value but does not fully compensate for the undocumented timeout parameter.

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 a specific verb ('Despliega'), a resource (cursor-agent agents), and the distinctive parallel execution model with isolated worktrees/branches. It differentiates itself from plan_run by explaining that each task behaves like an individual plan_run done in parallel.

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?

It provides clear guidance on when to use the tool: for independent tasks that should run simultaneously without conflicting. It gives concrete examples and implies it should not be used for dependent or conflicting work, though it does not explicitly name alternative tools to use in those cases.

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