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

Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description's real contribution is data provenance: player-observed relations backed by 'listed where 3 installs agree' with install count and last seen, versus game-file-derived relations explicitly flagged 'unconfirmed' with their source build. That confidence signalling materially changes how an agent should trust and present results, and the corpus scope ('authorized public corpus and the committed client layer') is useful context.

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?

Scope is front-loaded in the opening clause, and the two sentences carry dense but purposeful content. The parenthetical provenance blocks are heavy, but each earns its place by distinguishing confirmed from unconfirmed data.

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 9 relation types, 9 kinds, a direction axis and an output schema present, the description supplies the missing envelope: direction semantics are reinforced and data provenance is clarified. The notable remaining gap is the absence of any when-to-use framing, which is scored separately under usage guidelines.

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 100%, so all five parameters including rel, kind, direction and limit are already documented with descriptions and enums. The description's relation list loosely maps to rel enum values and 'Ids are the game's own' echoes the id description, adding little beyond the schema; baseline 3 is appropriate.

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 first sentence states a precise verb and resource: it returns 'every typed relation of one entity, both directions,' and enumerates the concrete relation types (dropped by, sold by, reagent for, same icon). An agent immediately understands this is a relation-graph lookup rather than an entity fetch, though no sibling tool (e.g. get_entity) is named to sharpen the contrast.

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?

The description never states when to reach for this tool versus get_entity, search, or item_page, nor any prerequisite or exclusion. Provenance and direction are explained, but that is output content, not usage guidance.

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