find_product_opportunities

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose useful traits: the 15-idea cap, the built-in starter list fallback, and the ranking-by-score behavior. However, it doesn't state whether this makes external API calls, whether results are cached/free, or what happens with more than 15 ideas (implied truncation only). It's a legitimate read-style operation on the surface, but the description leaves side-effect and limit details to inference.

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?

Three sentences with zero waste: purpose and criteria front-loaded in sentence one, the optional-input behavior in sentence two, and the follow-up routing in sentence three. Every clause earns its place; nothing is redundant or sprawling.

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?

An output schema exists, so the description needn't explain return values, and it correctly omits them. It fully covers the screening criteria, the optional input behavior, and the recommended follow-up. The only minor gap is the unspecified handling of inputs exceeding 15 ideas or empty/invalid idea lists, which would be useful edge-case context for a tool with zero required parameters.

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 0%, so the description must compensate, and it largely does: the criteria map to parameters (30%+ margin ↔ min_margin, under 500 g ↔ max_weight_grams, affordable first order ↔ max_investment, omit product_ideas ↔ built-in list). It doesn't explicitly restate marketplace or each parameter name, but the conceptual mapping is clear enough for an agent to set sensible overrides. High value added over an empty 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?

The description uses a specific verb ('Screen') with a quantified resource ('up to 15 product ideas') and exact criteria (₹199-₹699 price, under 500 g, 30%+ margin, non-seasonal, affordable first order), then states it 'rank[s] them by opportunity score.' It clearly distinguishes itself from the sibling research_product by presenting itself as the shortlisting step, so an agent can tell them apart.

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 names the when-to-use context ('Use this to shortlist') and the alternative next step ('then run research_product on the winners'). It also includes the conditional behavior for product_ideas ('Omit product_ideas to screen a built-in starter list'), so an agent knows exactly when and how to invoke it versus alternatives.

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