load_latest

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

With no annotations, the description carries the full burden and does real work: it discloses the selection algorithm (newest mtime across quicksave/autosave), the required game state before invocation, and that the result carries a `seat`. It omits failure behavior (e.g., what happens if no save exists) and whether the load is destructive to current state, so it falls just short of exhaustive.

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-loaded with the core rule ('load whichever save has the newest mtime') and each subsequent sentence adds a distinct, non-redundant fact: the sibling comparison, the precondition, the return field. It is slightly dense and multi-clause, but no sentence is filler.

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 zero-param action with no output schema, the description supplies everything needed to call it correctly: selection logic, sibling routing, precondition ordering, and a note about the returned `seat`. No material gap remains.

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?

The tool takes zero parameters, so there is no per-parameter semantics to document; baseline is 4. The description correctly spends its words on behavior instead of inventing argument detail.

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+resource (load the newest save) and defines the exact selection rule (quicksave OR autosave by newest filesystem mtime). It explicitly distinguishes itself from its closest sibling, load_save, so an agent can tell them apart without opening either 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?

Gives explicit when-to-use (resuming after a crash), a named alternative and why to prefer this one over it (load_save only checks quick/manual saves), and a hard precondition (must be in fresh main-menu state, run exit_to_main_menu first). Nothing is left to inference.

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