get_supplier_exposure

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses confidence values, match_method, the never-exact cross-source rule, default output scope (exact/probable, max 20 rows, no evidence), and the inference boundary (supplier-level, not contract-level). This is strong behavioral disclosure.

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 dense but front-loaded with the core purpose; every sentence covers a distinct semantic point such as claim, confidence, cross-source limitation, and default behavior. It is slightly rambling and uses capitalization for emphasis, but it earns its length.

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 tool with 4 optional parameters, no output schema, and no annotations, the description provides strong domain semantics but still lacks explicit parameter-to-field mapping and a clear statement of the output row format or how a key changes evidence. An agent could call it but might guess wrong about award_id/company_id and min_confidence.

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 text must explain the parameters. It hints at 'bez kluca' (without a key) and mentions confidence levels and the 20-row limit, but never maps award_id/company_id to 'key', never defines limit, and leaves min_confidence's 'probable'/'weak' enum unexplained relative to output confidence exact/probable/weak. Most parameter semantics are still guesswork.

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 opens with a clear verb and resource: it links contracts (kontraktu) to FDA shortages/recalls (vypadkom alebo stiahnutim). It also states the exact claim and non-claim, which distinguishes this from sibling list tools such as list_drug_shortages and list_federal_drug_contracts. This goes well beyond a tautology and gives an agent a precise mental model.

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 context for when this is appropriate: cross-referencing government contracts with FDA shortage/recall data. It also includes an explicit 'NETVRDI' caveat warning against over-interpreting results as drug-level attribution. It does not name alternatives or provide when-not scenarios beyond that caveat, so it does not reach a 5.

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