Submit one ZCode coding task

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

With no annotations, the description carries the full burden and does so well: it discloses async detached execution, that a TaskReceipt is returned immediately, that 'completed' means only invocation/report normalization finished and NOT master-agent acceptance, and that the master must independently review the diff and checks. These are exactly the non-obvious behavioral traits 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?

It is longer than typical but front-loaded, with the core purpose first and the critical 'completed ≠ accepted' caveat near the end. Nearly every sentence carries load (worktree rules, model scoping, async semantics), though the worktree/Bridge point is stated twice.

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 12-parameter mutation tool with no annotations, it covers the highest-risk aspects: worktree ownership, model scoping, and result interpretation. An output schema exists, so return-value detail is not required, yet it still clarifies the receipt's meaning. The gap is the unexplained bulk of array/scalar task-package parameters.

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 only partly does: it explains workspace, worktree_path, and the nested model object's effect. It says nothing about task_id's pattern, requirements, allowed_paths/forbidden_paths semantics, acceptance_criteria, test_commands, timeout_ms, or context, leaving most parameters undocumented in both places.

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 first sentence names a specific verb and resource — 'Create a bounded coding task' — and identifies the actor ('local ZCode subordinate agent'). This cleanly separates it from siblings like zcode_continue, zcode_cancel, and zcode_result, which operate on tasks that already exist.

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 gives concrete conditional guidance: decide whether to create a worktree, pass its existing absolute directory as worktree_path, and if omitted ZCode runs in workspace. It also clarifies that the Bridge never creates/selects worktrees and that model only affects the session. It stops short of explicitly naming when to prefer a sibling (e.g., continue vs a new task).

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