lookup_spell

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It conveys the accepted input forms (Chinese/English name, slug) and what is returned (data, Chinese name, source), which is useful. However, it does not disclose the no-match behavior, matching semantics (exact vs. fuzzy, partial names), or response shape, and the read-only nature is only implied by the verb 查.

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?

A single well-structured sentence leads with the query contract and follows with the return payload. Every chunk adds value — the resource, the two accepted query forms, and the three return components. No filler or repetition.

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 one-parameter tool with no output schema and no annotations, the description covers the purpose and the accepted query form, but the returned '数据' remains underspecified — the agent cannot know the shape or the detail level of the returned spell entry. No-match behavior is also unspecified, so the agent has limited understanding of edge cases.

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 is nearly bare — the single required 'query' is just a string with 0% coverage. The description compensates by defining what the query accepts: a spell name in Chinese or English, or a slug. This is essential semantic content that the schema alone lacks. It does not specify normalization or case handling, so marginally short of a 5.

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 a specific verb (查/look up), a concrete resource (SRD 法术/spells), and the query surface (name in Chinese or English, or slug). It also enumerates the returned payload (data, Chinese name, source citation). This functionally distinguishes it from sibling lookups like lookup_monster, lookup_condition, and lookup_rule, even without naming them explicitly.

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?

Usage context is only implied: an agent can infer this tool is for fetching spell data when it has a name or slug. There is no explicit statement about when to prefer it over related spell tools (spell_save_dc, spell_attack_bonus) and no exclusions or failure scenarios (e.g., no match). Guidance is adequate but strictly implicit.

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