start_motion_plan

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

With no annotations, the description carries the entire burden and does so: isolated per-run worktree copy, upstream project never written with pre/post SHA-256 manifests, timeout kills the process tree and yields TIMEOUT rather than a false 'no path exists', idempotent retries via request_id, and single-run concurrency. This is exactly the mutation-safety and failure-mode context an agent needs.

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?

Front-loaded with the action and its scope, then parameter notes, then the return/poll hint and concurrency rule. Every clause is informational, but the dense semicolon-chained parameter block makes it slightly harder to scan than a cleanly structured description.

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 an asynchronous, sandboxed, mutating planning job with an output schema present, the description covers initiation, isolation guarantees, timeout behavior, idempotency, concurrency, and the polling handoff. Nothing an agent needs to invoke it correctly is missing.

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%, and the description compensates fully for all four parameters: task_id naming pattern, planner whitelist ['Lazy_PRM'] applied to the worktree config, time_budget_seconds bounds 10-1800 with default 120 and expiry semantics, and request_id's regex plus idempotency purpose.

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 specific verb and resource ('Start ONE real offline planning run for a New_Design seed task') with clear scope: one run, seed task namespace, isolated worktree. The terminal clause 'poll get_plan_status' plus 'Only one real run at a time' separates it from the read-only sibling tool that reports results.

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 gives clear usage context: form the task_id as 'ND-SEED-<seed>', start the run, then poll get_plan_status rather than waiting. It also states the concurrency constraint ('Only one real run at a time'). It stops short of explicitly excluding alternatives such as validate_motion, so it is not a full when/when-not statement.

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