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

Even though annotations already mark this read-only, idempotent, and non-destructive, the description adds essential behavioral disclosures: round is a loose free-text containment match, type may be inferred from personaTags/canOffer rather than self-reported, project mode includes records where fundraising is null but financingNeed has a value, BP files are never returned, and the dataset is small enough to filter in memory. These are exactly the kind of non-obvious behavioral caveats an agent needs.

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 long but tightly structured with clear sections (何时用, 组合链, 口径/坑) and bullet-like caveats. Each sentence adds decision-relevant information or prevents a costly mistake, such as the BP URL prohibition and the round matching caveat. The examples are concrete and the layout makes the content easy to scan.

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?

With no output schema, the description provides the key fields for downstream chaining (items[].user.id, items[].company.slug, items[].product.slug, hasBp), covers both side-specific data quirks, explains what cannot be returned (BP files), and clarifies pagination behavior. For a complex dual-mode list tool with data-quality caveats, this is comprehensive.

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 100%, so the baseline is 3, but the description adds meaningful parameter semantics: side is tied to concrete user intents, round gets matching rule and example values, type is flagged as inferred/not authoritative, and offset is described with the nextCursor convention. Only limit gets no extra explanation, but its schema description is already sufficient.

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 explicitly states a dual-lens search: side=investor finds investors (个人/产投/机构) and side=project finds projects currently fundraising. It provides concrete user-phrase examples ('帮我找看 AI 应用的天使' vs '最近有哪些一人公司在融钱') that make the tool's purpose and scope unmistakable.

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 '何时用' section gives clear selection criteria with concrete examples, and the combination chain tells the agent exactly how to follow up (get_creator, start_conversation, follow_creator, get_company, get_product, set_my_role_profile). It does not explicitly contrast list_funding with sibling listing/search tools like list_creators or search_people, but the examples and routing guidance make when-to-use clear.

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