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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds genuinely useful behavioral context beyond this: ship/pirate wrecks persist indefinitely while jettison containers despawn after 10 minutes, with cargo settling into matching deposits. This tells the agent that results are time-sensitive for certain wreck types, which is valuable operational knowledge not derivable from the annotations.

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?

The core purpose is front-loaded in a single clause, with the parenthetical adding only high-value context: what wrecks contain, response module fields (name, type, instance ID), and persistence rules. Every sentence earns its place, though the parenthetical is slightly dense and could be split for readability.

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?

Since there is no output schema, the description compensates by disclosing that each module in the response includes name, type, and instance ID, plus persistence semantics that affect interpretation of results. Minor gap: the overall response envelope (wreck-level identifiers needed for subsequent loot_wreck/scrap_wreck calls) is not specified, but for a simple one-param listing tool the coverage is solid.

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% — session_id is fully described in the schema and is a single, standard parameter. The description adds no additional parameter meaning, but none is needed. With full schema coverage, the 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?

States a specific verb ('List') + resource ('wrecks') + scope ('at your current POI'). The description makes clear this is a read-oriented discovery tool, which differentiates it from mutating siblings like loot_wreck, scrap_wreck, sell_wreck, and tow_wreck that act on wrecks rather than listing them.

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 implies the usage context — you call this to see what recoverable wrecks exist at your location before deciding to loot or scrap them. However, it never explicitly names alternatives (e.g., loot_wreck, scrap_wreck, sell_wreck for acting on wrecks) or states when NOT to use this tool, so an agent must infer the routing from the tool name rather than the description.

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