plan_run

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

With no annotations provided, the description carries the full disclosure burden. It does disclose async-by-default behavior (wait:false) and the return shape (worktree + job_id), which is genuinely useful. However, for a mutation tool that creates worktrees and launches agents, it omits side effects, permission requirements, and implications of worktree creation — notable gaps for a write-heavy operation.

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?

Three sentences with the core purpose front-loaded and no filler. The async/return info is placed efficiently. Minor colloquial flavor ('al toque') adds no functional value but doesn't harm clarity.

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 complex tool with 12 parameters, no annotations, and no output schema, three sentences are inadequate. It fails to cover the plan/plan_file mutual exclusivity, the read-only mode option for analysis-first workflows, branch auto-generation, worktree path behavior, or how this compares to plan_run_parallel — all decision-relevant for an agent.

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 only 25% (3 of 12 params documented: mode, plan, branch), so the description must compensate. It only hints at the wait parameter's default behavior and adds nothing about plan vs plan_file, label, model, worktree_path, link_node_modules, timeout_seconds, base, or repo_path — leaving 9 params effectively undocumented across both schema and description.

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 combined action (crea el worktree Y lanza cursor-agent) in a single call, which is a clear verb+resource pairing. It positions itself as the recommended all-in-one flow, which distinguishes it from worktree_create and run. However, it doesn't explicitly differentiate from the sibling plan_run_parallel, leaving a minor ambiguity about when each combined flow is preferred.

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 names the recommended usage context ('el flujo recomendado para dale este plan a Cursor'), giving a clear when-to-use signal. But it provides no explicit exclusions or alternatives — it never says when to use run alone, worktree_create alone, or plan_run_parallel instead, leaving the agent to infer routing from the name and sibling list.

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