load_save

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

With no annotations, the description carries the full burden and does well: it discloses a hard state precondition (fresh main-menu, not mid-game), the filename format constraint, and non-obvious result semantics for the returned `seat` (auto seats re-detected, hotseat keeps default, set_seat overrides). It omits failure behavior (missing/invalid save) and whether loading discards 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?

Three sentences, front-loaded with the action and the parameter format, then the precondition, then result semantics. Dense but each sentence earns its place; the final `seat` sentence is somewhat compressed but not wasteful.

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 one-parameter state-changing tool with no annotations and no output schema, the description covers the identifying action, the parameter format, the state precondition, and the shape of the returned answer. Nothing essential for a correct call is missing.

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 0% and the schema names nothing but 'filename', yet the description fully compensates: bare name, no path, no .Civ5Save extension, with two concrete examples including one with spaces. This is exactly the format detail an agent would otherwise guess wrong.

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 and resource (load a save) with the exact scope ('from the main menu by its bare name'), which distinguishes it from siblings like load_latest (most recent save) and quick_save (writing a save). An agent can identify this tool without opening the schema.

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?

Explicitly states the precondition and exclusion ('Only works from a fresh main-menu state, not mid-game: exit_to_main_menu first'), naming the prerequisite tool to call. It does not, however, compare against the obvious alternative sibling load_latest, so the routing between the two load tools is left implicit.

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