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

With no annotations, the description carries the behavioral burden. It usefully discloses the corpus size and that trade_type is a semicolon-joined string with example values, which is real behavioral context. However it omits the schema-level pagination caps (limit hard cap of 20, offset+limit ≤1000) from the prose and says nothing about permissions, read-only nature, or result shape – understandable gaps for a search tool but not fully compensating for zero annotation coverage.

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 tight sentences, front-loaded with what the tool does and the data it exposes, then the key filtering caveat. The parenthetical table/count is minor implementation detail but earns its place as scale context with no filler.

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 an 8-param, all-optional search tool with full schema coverage, no annotations, and no output schema, the description supplies the domain scope and the one non-obvious parameter (trade_type semantics). It is reasonably complete; only pagination/return-shape behavior is left to the schema.

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 coverage is already 100%, so the baseline is 3. The description exceeds the baseline by explaining that trade_type is a semicolon-combined string and enumerating concrete values (授权/许可、投资;期权;合作、并购), which meaningfully extends the bare schema text '交易类型关键词' and warns the agent about multi-value 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?

States a specific verb+resource (检索 BD 交易) and enriches it with the underlying table (fa_drug_trade), the corpus size (~4k), and the domains covered (license-in/out, upfront, total amount, milestones, counterparties). This clearly identifies the tool and differentiates it from sibling detail getters like get_deal_detail, though it never names a sibling directly.

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?

No explicit when-to-use guidance and no comparison with overlapping siblings such as search_investments, search_companies, or get_deal_detail. The trade_type note hints at how to filter but not when this tool is the right choice over alternatives.

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