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

The description explicitly notes 'no game secrets', adding a behavioral boundary beyond the schema. However, with no annotations, it doesn't state whether it is read-only, what the exact return shape is, or any error cases, leaving some transparency gaps.

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?

Two short bilingual sentences deliver the core purpose and a key usage note without waste. Front-loaded with 'Save metadata' and immediately followed by scoping details.

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 simple metadata lookup with one optional parameter and no output schema, this description is sufficient: it explains what metadata is included/excluded and the prerequisite. It could mention return format, but that's not essential given the tool's simplicity.

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 input schema covers 100% of the parameter and includes a detailed description (save code format and prerequisite). The tool description adds little beyond this, so the schema carries the explanatory burden; 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 description clearly states it retrieves save metadata with specific components: path, schema version, identity mode, and progress summary. This distinguishes it from siblings like fishing_play (gameplay) and fishing_share_card (sharing), giving a specific verb ('save metadata') and resource scope.

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 provides actionable guidance: if no player_code, play once first to obtain it. This clarifies a prerequisite and a typical usage flow. It doesn't explicitly contrast with alternatives, but the context is strong enough to imply when this tool is appropriate.

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