move_npc_group

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

With no annotations, the description carries the full burden, and it does disclose one genuinely non-obvious trait: the target is advisory and NPC AI may pick a different one after simulation resumes. It omits whether the call requires held control, whether it persists across ticks, and what an invalid or stale request does.

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?

Two short, front-loaded sentences with no filler. The brevity is appropriate as far as it goes, though it edges toward under-specification rather than true economy.

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 seven-parameter, six-required mutation-ish tool with no annotations, no output schema, and low schema coverage, two sentences are far from sufficient. An agent must guess at coordinate semantics, the role of virtual, request_id idempotency, and the control-lease precondition.

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 only 29% (lease and session_id are described in the schema), and the description adds no meaning for x, z, virtual, group_id, or request_id. It never even states that x/z are the target coordinates, so it does not compensate for the coverage gap.

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: 'Submit a native movement target for a nonplayer group.' An agent knows this queues movement for an NPC group rather than a player squad, but 'native movement target' is unexplained and nothing distinguishes it from siblings such as move_squad.

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?

There is no explicit when-to-use guidance, no prerequisites stated, and no routing to alternatives. The closest thing is an implicit hint that this sets an advisory target, and the fact that a control lease is required is only discoverable via the lease parameter's schema description.

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