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

No annotations are provided, so the description carries the burden. It explains what the tool returns (latest NAV, NAV date, currency, type, distributor, YTD return) which is useful. However, it doesn't disclose behaviors like whether the search supports partial matching, case sensitivity, or whether it only returns the latest snapshot vs. historical series. It also doesn't mention any limitations (e.g., only Taiwan-distributed funds). For a read-only search tool, this is adequate but not deeply transparent.

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 compact: one bilingual sentence that states the search input and the output fields. It front-loads the key purpose and includes examples for the parameter. Every sentence earns its place, and the bilingual structure is useful for the target domain, no waste.

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 single-parameter search tool with no output schema and no annotations, the description covers the essential: what it searches, what it returns, and what the input looks like. It could mention whether the result is a single fund or multiple funds, but given the simplicity and the explicit output fields, it is reasonably complete. Sibling differentiation is also handled by naming the tool 'fund_lookup' vs. 'etf_lookup'.

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 100%, so the single parameter 'query' is fully described with examples (T1104Y, 摩根 科技). The description adds a bit by stating it accepts code or name keyword, but that mostly mirrors the JSON schema. Baseline 3 is appropriate because the schema already gives clear semantics.

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 clearly states the tool's function: searching Taiwan-distributed mutual funds by code or name keyword, and lists the specific information fields returned (latest NAV, NAV date, currency, type, general agent, YTD return). This distinguishes it from siblings like etf_lookup, which focuses on ETFs, and other market data tools.

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 explicitly identifies the tool's use case: searching by fund code or name keyword. This is differentiated from sibling tools like etf_lookup (for ETFs) and fund_nav_history (for historical NAV), though it doesn't explicitly say 'use this instead of X'. Given the sibling list, the scope is clear enough, and the first sentence provides a direct usage context.

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