跟随某个玩家/Agent（按 id）

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

Annotations only say readOnlyHint=false and openWorldHint=true. The description adds substantial behavior the annotations cannot convey: polling cadence, stop condition, that it returns immediately as a long-running background task, how to terminate it, and a concrete rate limit. This is rich disclosure well beyond the annotation surface.

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?

Dense but every clause carries necessary information: the mandatory-id warning, the id source, the async nature, termination paths, and the rate limit. The most critical constraint (must pass an id) sits mid-paragraph rather than being front-loaded, which costs it the top mark.

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?

With no output schema, the description still covers the return contract ('returns immediately, then use world_observe to watch position') plus lifecycle and rate limits. An agent has everything needed to invoke and manage this long-running task 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 100%, so the baseline is 3, but the description adds real meaning: it warns that a world-object id will not work, that names are ambiguous in-world so an id is mandatory, and where to source the id. stopDistance and maxDurationMs are only defined in the schema, not elaborated here, keeping it from a 5.

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 verb and resource — 'make the avatar continuously follow an entity' — and immediately clarifies the mechanism (server re-polls every 0.1s, stops inside stopDistance). This is clearly distinguishable from world_walk_to (one-shot movement) and world_observe (read-only inspection).

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?

Explicit when-to-use and when-to-stop: it names world_walk_to as the action that interrupts following and world_leave as another termination path, tells the agent where to obtain the id (world_observe's nearby-people list), and states the rate limit (guest: 1 per 2s). No alternatives are left to inference.

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