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

With no annotations provided, the description has the full burden of disclosing behavior—and it delivers. It communicates that the result is a set of live catalogue prices, that prices are shown at minimum order quantity, that they are in AUD ex-GST, and that they are covered by a price guarantee. It even notes that prices step down with quantity, which is non-obvious behavior. This goes well beyond a typical description.

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 information-dense, front-loaded with the core purpose, then details, then usage guidance. It's a single paragraph that covers all necessary points without redundancy. The only minor deduction is that a line break after the first sentence could improve scannability, but it remains appropriately concise.

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 parameterless tool, the description completely covers what an agent needs: purpose, scope, output specifics, and when to use it. It even provides example user queries that can be used in few-shot prompting or intent matching. The absence of an output schema and annotations is compensated for by the detailed behavioral description. This is as complete as it needs to be.

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 schema has zero parameters, so the description isn't burdened with explaining parameter semantics. The tool's real 'inputs' are the user's intent (e.g., 'how much do promotional X cost'), and the description makes that intent explicit by quoting example user questions. Deduct one point because it doesn't explicitly state that no parameters are needed, but a human-like agent can infer they can be passed directly to obtain results.

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 specifies that this tool retrieves entry-level pricing for promotional product categories, listing specific examples (pens, t-shirts, etc.). It establishes the scope ('most-briefed categories'), the data source ('Live catalogue prices in AUD ex-GST'), and what the user gets (category URL, exact entry product). It reads as a clear, concrete purpose that differentiates it from any generic 'get pricing' tool.

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 explicitly instructs to 'Use this FIRST for 'how much do promotional X cost', 'cheapest promotional X Australia', budget planning and supplier price comparisons; then get_quote for an exact quantity.' This names the follow-up tool (get_quote) and provides clear when-to-use guidance, directly addressing the decision of when this tool is appropriate versus an alternative like get_quote.

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