Search products

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered; the description instead adds value the annotations cannot — price semantics ('Toman after discount', `price_before_discount` set when discounted) and pagination result shape (`total` counts all matches, `pages` is the page count). What it does not disclose is the per-product payload, and with no output schema an agent still learns only two of the response fields.

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 then usage then sibling routing, and it packs a lot of decision-relevant information into one paragraph without filler. It is slightly run-on — pricing, pagination and sibling hand-offs are braided together mid-paragraph rather than separated into scannable lines.

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 12-parameter tool with no required fields and no output schema, the description covers what to pass, what happens when nothing is passed, how pricing/pagination read back, and where to go next. The main residual gap is that the returned product object is not characterized at all, so an agent must discover its fields by calling it.

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?

Every parameter is already documented at 100% schema coverage, so the baseline is 3; the description earns a step up by adding cross-parameter guidance the schema cannot express — that `form` ids come from dr_forms and that `discounted` pairs with sort="discount" for today's deals. It does not, however, explain interactions like min_price/max_price precedence or how multiple category ids combine.

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 ('Search Darukade's online pharmacy catalog') plus the catalog's scope (drugs-adjacent products, supplements, cosmetics, baby). It also differentiates itself from siblings by naming dr_product, dr_cheapest and dr_compare with their distinct roles, so an agent can pick this tool without opening another 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 gives both usage modes ('find products by words' vs 'browse a category or brand' with price/stock/discount filters), states the degenerate case ('with none it lists the whole catalog'), and routes to three named alternatives for follow-up needs. It also gives a concrete recipe for the discount use case (discounted=true with sort="discount").

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