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

With no annotations, the description carries the full burden and does so richly: 3-factor ranking, shop-tier ordering, mode semantics, live fan-out to taobao/jd/pdd union APIs with ~1s latency cost, working buy_url on live-only items, and a read-only declaration. It also warns not to invent review text, which is unusually strong behavioral context.

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?

Front-loaded with purpose and the preferred-over routing before any mechanics. It is dense and parenthesis-heavy, but every clause (ranking, tiers, mode, live, reasons, read-only) earns its place, so waste is minimal.

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 tool with no output schema, the description explains the return shape (score + breakdown.reasons), the ranking model, latency trade-offs, and safety. Combined with the dataset-specific routing guidance, an agent has enough to call it correctly.

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 50%, but the description adds real meaning for the two non-obvious params: mode (default balanced, with when-to-use for quality/price) and live (parallel fan-out, ~1s cost, coverage gain). It does not add anything for category, page_size, platforms, budget_min/max beyond the schema.

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 and resource ('SMART product search for shopping recommendations') and distinguishes itself from named siblings by declaring it PREFERRED over shelf_search/cps_*_search. An agent can route to it without opening any schema.

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?

Explicitly names the trigger ('help me buy X' asks) that selects this tool over alternatives. It further gives selection guidance for mode (pick price when cheap, quality when authenticity) and for live=1, leaving little to inference.

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