load_game

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

Beats the annotation baseline by spelling out exactly when success is false (empty slot, unreadable, wrong class) and how to disambiguate missing vs corrupt. It also implies object reinstantiation ('rebuilt as that'), which is consistent with destructiveHint=true and idempotentHint=false, though it never explicitly warns that loading re-creates objects and may disturb current game state.

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-loads the action and scope, then covers failure semantics, then lists the return shape. With no output schema present, enumerating the returned fields earns its space, though the run-on middle sentence is dense.

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?

For a 3-param tool with no output schema, the description supplies the return field list and the success/failure contract, which is what an agent otherwise could not know. The one real gap is positioning relative to load_game_async and load_game_from_memory.

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 slot_name, user_index and save_game_class are already fully documented in the schema. The description reinforces the class-mismatch failure tied to save_game_class but adds no syntax, defaults, or format detail beyond it. Baseline 3 applies.

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?

Specific verb (Load) plus resource (the SaveGame stored in a slot), and it even names the underlying engine call it wraps (LoadGameFromSlot). It distinguishes itself from siblings like load_game_async, load_game_from_memory and get_save_game_info by stating it loads and reports the transient loaded object.

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 explains the failure conditions and points at does_save_game_exist for separating missing from corrupt. However, with three close siblings (load_game_async, load_game_from_memory, get_save_game_info) it never states when to pick this synchronous slot loader instead of them, leaving the choice to inference.

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