observe

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

With no annotations, the description carries the full behavioral burden, and it does disclose two real traits: pagination behaviour is independent of entity type, and `detailed` enriches results with fluid/inventory/recipe/power/rail-connection data where supported. However it does not state the read-only/no-side-effect profile explicitly, does not explain how limit/offset interplay, and does not say what happens when area, radius and position are combined.

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?

Three short sentences, front-loaded with the core action, with no filler. The inline `area` shape note is placed usefully, though the block formatting makes it read slightly like an afterthought rather than an integrated parameter note.

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?

An output schema exists, so return-value explanation is rightly omitted, and the tool's core read semantics are conveyed. But for a 9-parameter tool with zero schema descriptions and no annotations, coverage of only 2 parameters leaves the agent guessing on most of the surface area, particularly the spatial-filtering 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 9 parameters, so the description must compensate and largely fails to. It documents only the shape of `area` ({left_top, right_bottom}) and the effect of `detailed`; limit, offset, radius, surface, names, types and position are left entirely undefined, including the important question of precedence between `area`, `radius` and `position`.

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?

"Read any entity prototypes in an area" names a specific verb and resource, and the following sentences make clear it returns world entities with their state data. It is distinguishable from a single-entity read, but the description never names inspect_entity or find_sites, so the boundary with siblings is left to the agent. The word "prototypes" is also slightly off-terminology for what is effectively an area scan of live entities.

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 or when-not-to-use guidance, and no alternative is named despite inspect_entity (single entity) and find_sites (search) being obvious near-neighbours. The agent must infer from "in an area" that this is the bulk/area read. That is implied usage only, with no exclusions.

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