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

There are no annotations, so the description must carry the burden. It mentions 'verified price spreads', '3+ retailers', and 'false-positive filters applied', which provides some insight into the tool's underlying logic. However, it doesn't describe the return format or any safety characteristics beyond being read-only by implication.

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 two sentences, both packed with relevant information. There is no redundancy or filler, making it highly efficient.

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?

The description provides enough context for a simple list tool: it explains the deal logic, offers an example query, and points to a related tool. It doesn't fully describe the output format, but for this tool, the return type is straightforward. The lack of an output schema raises the need for some return info, but the description gives a decent overview.

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?

The input schema describes 'context' and 'category' but leaves 'limit' without a description. The tool description doesn't mention any parameters or add further semantic meaning, so the agent must rely solely on the schema. Since coverage is at 67%, the description doesn't compensate for the missing 'limit' parameter.

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 tool returns 'Current best-value products across the UK market' with verified price spreads, and provides an example use case. It distinguishes itself from siblings by suggesting a follow-up with get_product_offers for purchase links.

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 explicitly says 'Good for "what are the best golf deals right now?"' which tells the agent when to use it. It also advises following up with get_product_offers for purchase links, implying when to use that sibling instead. However, it doesn't explicitly exclude other scenarios or mention alternatives like get_deal_intelligence.

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