record_learning

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

Only readOnlyHint=false is given, so the description carries the burden and does so well: it discloses overwrite-instead-of-duplicate semantics on repeat calls, that fact fields are auto-extracted server-side so the agent should not report them, and that standing_insight persists across games rather than being retired per game. These are exactly the behaviors an agent cannot infer from the annotation.

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?

Purpose and injection effect are front-loaded, then call timing, then per-field meaning. Dense but every sentence adds information; the only cost is slightly packed multi-clause lines that take a second read.

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 mutation tool with minimal annotations and zero schema description coverage, the description covers when to call, what each field means, what the server fills in, and overwrite/persistence behavior; an output schema exists so return values need no explanation.

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% — the schema is bare titles — and the description compensates for all three parameters: lesson is the single most memorable thing in one actionable sentence, result is the outcome with a concrete format example, and standing_insight is scoped to invariant rules-level lessons with a worked example.

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 — writing this game's lessons into a cross-game learning library — and adds the downstream effect (auto-injection into the next game's T1-T3 briefing). That effect alone distinguishes it from every read/side-effect sibling in the list.

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 says it is mandatory at end of game ('局末必调') and also permitted mid-game, and gives a clear decision rule for when to use standing_insight versus lesson ('只在确认是规则而非局势时用'). It does not name get_learnings as the read-side counterpart, so the sibling routing is left implicit.

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