观察周围（AI 的眼睛）

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

Adds substantial behavior beyond the readOnlyHint/openWorldHint annotations: rate limiting, per-tier radius ceilings, a ~2KB default byte budget, the graceful-degradation rule (distant objects downgrade to name-only while nearby descriptions stay complete), and a caveat that the server estimates y as a ground plane so height differences are unreliable.

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 tool's identity and purpose before the constraints, and nearly every sentence carries actionable information for a vision-less agent. It is dense and long, and a few clauses (the distance3D aside) could be trimmed, but nothing is filler.

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 carries the full burden of explaining returned content and it does: field semantics, byte budget, degradation behavior, and what the events section contains. An agent has everything needed to call and interpret this tool.

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 baseline is 3, but the description goes further: it explains the radius/maxBytes tradeoff and the remediation strategy (shrink radius and observe repeatedly, or raise maxBytes), and clarifies that distance is horizontal while distance3D is only an upper bound. That adds genuine meaning beyond the parameter docs.

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 concrete verb and resource: returns textual descriptions of nearby players, world objects, and portals, framed as 'the AI's eyes' since no 3D rendering is available. The description of what fields come back (object description text, events since last observation) makes the tool's output uniquely identifiable even without naming a sibling.

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?

Gives concrete usage guidance: start with radius 30m, expand or observe in multiple passes when you need distance, and adjust maxBytes to see more. Rate limit (1 per 2s) and tier-based radius caps are stated. However, it never contrasts with siblings like world_discover or world_chat_history, so the agent gets no explicit routing rule.

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