get_learnings

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

readOnlyHint=true already declares the safety profile, yet the description still adds real context: the always-on briefing only carries one-line summaries of the last 3 games, so this call is required to see the full record. That explains why an agent would pay a call here rather than rely on injected context. Size, volume, or paging of the returned library is not mentioned, but the output schema covers return shape.

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 short sentences ordered by value: what is in the library, when to call it, then how it differs from the briefing. Front-loaded and free of repetition; every clause adds information the agent did not already have.

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-parameter read tool with annotations and an output schema, everything needed to decide to call it is present, including the relationship to the auto-injected briefing. The one missing link is how entries get into the library, i.e. no pointer to the record_learning sibling, so the description is nearly but not fully self-contained.

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 no parameters, so there is nothing for the description to disambiguate and the schema-coverage rule sets a baseline of 4. No argument formats or filters are implied anywhere in the text, which is consistent with the empty input schema.

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 concrete verb and resource (查看 cross-game learning library) and enumerates the contents it holds: past-game results, lessons, fatal mistakes, plus invariant rules. That content profile is distinctive enough to separate it from get_diary or get_strategy_notes in practice. It never names a sibling though, so the differentiation is by implication rather than explicit statement.

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 two specific triggering situations: setting strategy at game start, or suspecting you are repeating a past game's mistake. That is clear usage context. It offers no exclusion guidance against the cluster of similar knowledge tools (get_diary, read_strategic_summary, get_strategy_notes, get_expert_playbook), which is what keeps it out of a 5.

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