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

Beyond the annotations (readOnlyHint, idempotentHint, openWorldHint), the description discloses several non-obvious behaviors: only products with complete data are returned, results are factually sorted by price rather than ranked, purchase completion requires KYC/AML, the agent never finalizes transactions, and IDFMETALE makes no price forecasts. This goes well beyond what the annotations alone communicate.

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 a single dense paragraph, front-loaded with the search purpose and then followed by operational and compliance caveats. It is slightly long, but every sentence earns its place given the financial/AML context; the disclaimer sentences could be compressed but are not redundant.

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 no output schema, the description must explain return semantics, but it only vaguely says it returns 'structured attributes + live from-price and availability.' It also omits details about limit/pagination, default currency, and exact result shape. It does cover important edge behavior like complete-data-only and no future-price promises, but not enough to fully compensate for the missing output schema on a 10-parameter tool.

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?

With only 30% schema description coverage, the description partially compensates by listing filter dimensions and clarifying that the text query narrows results rather than ranks relevance. However, it claims a 'próba' (fineness) filter and a price 'range' that are not fully represented in the schema (there is no próba field and only cena_max, no cena_min), which can mislead an agent. It also leaves limit, waluta, and dostepnosc semantics mostly implicit.

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 identifies a specific resource (the IDFMETALE investment-metals catalog) and describes a distinct filterable search behavior: filtering by metal, form, mint, mass, and price, and returning structured attributes plus live price and availability. This clearly separates it from sibling tools like get_product, get_live_price, and check_availability, even without naming them.

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 gives clear usage context: it is the catalog search endpoint, returns only complete data, and sorts by ascending price rather than relevance. It also provides explicit boundaries — the agent must not finalize transactions, KYC verification is required, and the data is not investment advice. It does not explicitly route to sibling tools, but the search-vs-single-record distinction is strong enough.

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