diana_glossary

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile needs no restatement. The description adds genuine context beyond that: the corpus is ~15,000 GUI-translation strings, which tells the agent the coverage is UI labels rather than documentation prose. It says nothing about matching behavior (partial/fuzzy, case sensitivity) or what happens when no pair is found.

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?

Two sentences plus a two-line Args block, with the corpus scope and the bidirectional use case front-loaded before the examples. Every clause carries information; the quoted examples do real work showing input format in both languages.

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 low-complexity lookup tool with an output schema (so return shape need not be described) and annotations covering the safety profile, this is close to sufficient: source, direction, examples and both parameters are addressed. The remaining gap is match behavior and no-result handling, which the description leaves entirely implicit.

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 carry the load, and it partially does: 'term: an English or Chinese term' clarifies language semantics that the bare title 'Term' does not, and 'limit: number of pairs' implies results come back as paired entries. However, limit's default of 12 and any upper bound are left to the schema, and matching semantics are unstated.

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 names a specific verb and resource ('Look up DIANA terminology') and pins down the exact corpus it searches ('DianaIE's own GUI translation, ~15,000 labels, options and messages'), which separates it from diana_keywords and diana_manual_search. It also states bidirectionality (English→Chinese and Chinese→English) with concrete examples. It stops short of naming the sibling tools it should be preferred over, so it is not quite a 5.

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 two usage cases are stated as the tool's function rather than as conditional guidance: 'the Chinese label the user sees for an English term, or the English term ... behind a Chinese label'. An agent can infer when this applies, but there is no explicit 'use this instead of diana_keywords/diana_manual_search when...' routing, and no exclusions.

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