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

With no annotations, the description carries the full burden and does substantial work: it discloses the returned data.list shape, that planList is split per population, that discount is a partner discount factor (e.g. 5 = 5折, null if none), and forbids fabricating items/costs. It omits error behavior, auth, and idempotency details, which keeps it from a 5.

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?

Everything stated earns its place, and the purpose plus input format is front-loaded before the return-value and prerequisite details. The single dense paragraph is harder to scan than a structured breakdown, which keeps it from a 5.

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 complex quotation tool with a free-form schema and no output schema, the description covers input field semantics, output shape, discount interpretation, the knowledge_get prerequisite, and the reservation.book handoff. Nothing an agent needs to call it correctly is missing.

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 0% and the schema is effectively free-form objects, so the description must supply all meaning — and it does: it enumerates each quote item's fields (tier, budget, healthConcerns, populations with man/lady/girl defaults) and explains partnerId is a UUID passed through for partner pricing.

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 opens with a specific verb+resource: enterprise group checkup quotation (企业团检报价), and immediately explains that quotes is an array with one plan per tier. An agent can distinguish it from siblings like plan_recommend or reservation_book because it names its own input structure and downstream handoff to reservation.book.

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?

It gives an explicit prerequisite: load knowledge_get({uri:"objects/checkup-proposal"}) as the system prompt before calling, and it states that planId must be passed to reservation.book rather than hand-assembling items. It does not explicitly contrast with alternatives like plan_recommend, so not a full 5.

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