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

Annotations only provide openWorldHint: true, which is a minimal disclosure. The description meaningfully adds behavioral context beyond this: the hard-coded two-year temporal window, the explicit statement of what is NOT included, and pricing cadence. It does not contradict the openWorldHint annotation (the description doesn't claim a closed/exhaustive result set). Slightly better disclosure of the open-world nature would push this higher, but the added scope and boundary info earns a 4.

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 and well-structured with clear labeled sections (涉及指标/类型, 不包含, 典型问法). It front-loads the core purpose before secondary details. Minor waste: the pricing JSON block is structurally irrelevant to tool selection, and the purpose statement slightly repeats the tool name's meaning. Overall efficient and scannable.

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?

Given the moderate complexity (2 params, an available output schema, and a large field of sibling park/chain tools), the description covers the essentials: what it returns (a list of bid-participating companies), the temporal bound, exclusions, and example mappings from natural-language queries. Since an output schema exists, the absence of return-format details is acceptable. Gaps: it never addresses the openWorldHint indication, and the count-vs-list phrasing is confusing enough to warrant clarification. Still, it is above the minimum viable level.

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% — both park_name and year already carry descriptive text in the schema ('园区名称，如「中关村软件园」…' and '统计年份，如 2024；可选'). With full schema coverage, the baseline is 3, and the description adds only marginal value: it reinforces park_name usage via typical-query examples. It does not clarify that the two-year window is fixed regardless of the year parameter or how the optional year interacts with the 2023–2024 window, which is a missed opportunity.

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 purpose: querying the list of enterprises that participated in tender bidding at a specific park within the last two years. It specifies the exact resource (park-based companies) and temporal scope, and the '不包含' section differentiates it from count-only siblings like park_participated_tender_company_num and from chain-based counterparts. However, the phrasing '仅返回数量不返回名单' is slightly ambiguous—it reads as if the tool returns counts, which contradicts the tool name—though contextually it means the tool does NOT cover count-only results.

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 provides clear context: it names the park-based scope, the two-year lookback window, and explicit exclusions (other enterprise classification statistics and count-only responses). It also supplies three typical query examples to guide invocation. However, it never explicitly names alternative tools (e.g., 'use park_participated_tender_company_num for counts only' or 'use chain_participated_tender_company_list for chain scope'), relying on the sibling list to imply them.

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