lookup_rule

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

No annotations are provided, so the description carries the behavioral burden. It explicitly discloses the most important behavior: a miss returns found=false and it never fabricates results ('绝不编造'), which is a major hallucination guard. It does not mention side effects (though a search tool likely has none), rate limits, or return structure, but the no-fabrication disclosure is significant and valuable.

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?

The description is a single compact sentence that front-loads the core action and then adds the crucial behavioral guarantee. There is no wasted wording, and the most important behavioral note (no fabrication) is included without bloating the description.

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?

The description leaves an important gap: it details the miss behavior (found=false) but does not describe what a successful hit returns. With no output schema or annotations, the agent does not know whether the raw rule text, metadata, or other fields comprise the result. For a simple tool with one input, the missing success-response details make it somewhat incomplete.

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%, so the description must compensate for the query parameter. It adds that query is a '关键词' (keyword), which is meaningful semantics beyond the generic 'Query' label. However, it does not provide examples, syntax, or constraints on the keyword type, so it only partially compensates for the lack of schema descriptions.

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 states the specific verb '关键词检索' (keyword search) and the resource 'SRD 规则条目' (SRD rule entries), which distinguishes it from sibling lookup tools such as lookup_monster, lookup_spell, and lookup_condition. This is a clear, resource-specific purpose that an agent can immediately understand and differentiate.

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 implies when to use the tool: when you need to do a keyword search against SRD rule entries. It is clear enough that an agent would use it over monster/spell/condition lookups, but it does not explicitly mention alternative or say when not to use it, such as preferring semantic_search for fuzzy queries.

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