Search Tenders

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

The description discloses a known behavioral quirk: the value_min/value_max filters are 'leaky at the API side' and results slightly outside the range can appear. This is valuable beyond what annotations could provide. However, no annotations are provided at all, so the description carries more burden; it doesn't mention pagination behavior, rate limits, or result count limits, but the leak warning is significant.

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 concise and front-loaded: the first sentence states the purpose, the second discloses the known leak caveat, and the rest are examples. The examples are helpful but take up space; still, for a 14-parameter tool they're valuable. It avoids fluff and every part contributes.

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 14 parameters, 0% schema coverage, no annotations, and a large sibling set, the description does a solid job: it gives the source (BZP + TED), warns about leaky filters, and provides three representative example calls covering common use cases. It doesn't document the output schema (but an output schema exists, so that offset applies), nor explicitly state which filters require what conditions, but the examples partially cover that. The lack of explicit date format guidance is a minor gap.

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 schema only provides property names, enums, and defaults. The description compensates by showing example parameter combinations: search='komputer', city='Kraków', notice_type='ContractNotice'; buyer_nip, cpv, sort; cpv, province, value_min, sort. These examples clarify how filters combine and how sort values work ('newest', 'value_desc'). The description still doesn't explain format of date_from/date_to or the exact meaning of order_kind, but the examples provide substantial guidance.

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 states the tool's purpose: 'Search Polish public tenders (BZP + TED) with filters.' It uses a specific verb ('search') and resource ('Polish public tenders'), and the mention of BZP + TED adds scope. It also distinguishes itself from siblings like get_tender, which is for retrieving a single tender, and search_entities/search_cpv for other entity types.

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 three concrete usage examples showing filter combinations, which implicitly teach when to use it. It doesn't explicitly state when not to use it or name alternatives, but the examples and the tool name 'search_tenders' make its context clear. It could be improved by explicitly saying 'use get_tender to fetch details for a specific tender ID.'

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