Show products

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is low, but the description adds genuinely non-obvious behavior: rendering is client-dependent — claude.ai and ChatGPT draw cards, other clients receive the same data and should list items with each URL. That fallback instruction is valuable and not encoded anywhere in the structured fields. It stops short of noting any limits on how often it should be called.

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-loads the what (cards with fields) before the when, and every clause carries information. Slight redundancy between 'Use it after hktv_search to present picks…' and 'Call it whenever you recommend products', which restate the same trigger from two angles.

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 only two shallow parameters, full schema coverage, and an output schema covering the return shape, the description needs to supply only behavior — which it does, including the client-specific rendering fallback. Nothing required 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 description coverage is 100%, with both `items` and `title` fully documented ('in the order to show them', 'Heading above the cards'), so the baseline of 3 applies. The description names the note and link but adds no ordering, limit, or id-provenance detail beyond what the schema already states.

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 (show/present) and resource (products you picked) and enumerates exactly what the rendered card contains — photo, price, unit price, rating, delivery, note, HKTVmall link. That distinguishes it from hktv_search (find) and hktv_get_products (fetch raw data) without requiring the schema to be opened.

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 preceding step ('Use it after hktv_search') and the alternative it replaces ('instead of a long text list'), plus a proactive trigger ('Call it whenever you recommend products, without being asked'). An agent knows both the sequence and the condition for invoking it.

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