get_expert_playbook

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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real context beyond that: each entry carries a confidence level and a source tag (rule mechanic / community consensus / local empirical), and a turn value filters out entries outside their applicable window. It does not, however, say anything about result volume, ordering, or what an empty result means.

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?

Dense but purposeful: the resource and its scope come first, the sibling differentiation second, the invocation modes third, and the decision trigger last. Every clause carries information; the only slight looseness is the long enumeration of covered topics.

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?

With an output schema present the description needn't explain return structure, and it still characterizes what entries contain (confidence + source). Combined with the mode explanation, an agent has enough to call it correctly; the missing piece is any hint about valid topic vocabulary for the one free-form string parameter.

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 description coverage is 0% and the two parameters (turn, topic) only have type/default in the schema, so the description must compensate. It does explain the semantics of each mode — no-arg returns the catalog, topic looks up by subject, turn filters by applicability window — but gives no example topic values or accepted formats, so an agent still has to guess what strings are valid.

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 (查高玩知识库 — retrieve the expert playbook) and enumerates the actual content: expansion pacing baselines, barbarian mechanics, war-declaration windows, difficulty bonus tables, victory-route checklists. It explicitly contrasts itself with the sibling get_strategy_notes (civilization-specific vs. civilization-agnostic), so an agent can pick between them 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 concrete when-to-use guidance ('worth reviewing before major decisions like settling, declaring war, expanding') and names the alternative (get_strategy_notes) with the condition that selects it. It also spells out the three invocation modes, so the agent knows how to call it in each situation.

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