build_level

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

With no annotations, the description carries the full behavioral burden and does so fairly well: it discloses the 24-module cap, that invalid plans fail before editor mutation, and that checking uses sampled standing capsules rather than a NavMesh or full controller simulation. It omits what remove mode destroys, permission/auth needs, and return behavior, but the failure semantics and validation limits are genuinely informative.

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?

Purpose is front-loaded and the dense settings block follows in a single compact stanza with no filler sentences. The prose block is somewhat run-on and merges schema-like detail with behavioral caveats, but every sentence carries information.

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 no-annotation, no-output-schema tool with a free-form settings object, the description covers construction constraints, failure conditions, and check fidelity. What is missing is the mode semantics (valid values and effect of remove) and any indication of what the call returns; otherwise it is sufficient to call correctly.

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 coverage is 0% across 3 parameters, so the description must compensate. It documents the settings object in rich detail (modules structure, cell/kind/direction enums, cell_size, story_height, door dimensions, capsule metrics, max_step, position, yaw), but says nothing about level_id and only implies the mode values through the leading verb list.

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 opening clause names a specific verb set (plan/build/check/remove) and a well-defined resource (connected modular level with collision clearance), which maps directly onto the modes it supports. No sibling tool does level building, so an agent can distinguish this from edit_scene, compose_scene, or arrange_props without opening any schema.

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?

Usage is implied by the mode verbs and constraints (max 24 modules, stairs need two landings, disconnected plans fail), but the description never explicitly says when to choose this over siblings like edit_scene or compose_scene, nor when-not to use it. It gives enough context to operate but leaves routing to inference.

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