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

Annotations already provide readOnlyHint=true, and the description goes well beyond that by disclosing performance tradeoffs ('all' slower), the meaning of total capping at 10,000 (i.e., '10,000 and more') when includeTotal=false, exact quotas per account tier, and the error behavior when limits are exceeded. This is substantial behavioral context that helps an agent anticipate results and failures.

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 information-dense and front-loaded with the core purpose, then proceeds to return fields, performance/limit behavior, and quotas. While it is longer than the minimal two-sentence style, every sentence contributes meaningful operational context (availability, limits, error handling) that an agent needs. It is well-organized and avoids fluff, though it could be tightened slightly.

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?

Given 10 parameters, no output schema, and no required fields, the description covers essential operational aspects: returned item fields, pagination indirectly via schema, period behavior, total semantics, quotas, and error handling. It does not explicitly explain parameter combination or sorting, but the schema covers individual parameters, and the description provides enough context to call the tool correctly without ambiguity.

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?

The input schema has 100% parameter description coverage, including details for period, includeTotal, regionCodes, customerInns, etc. The description adds a high-level summary of filter categories and repeats the includeTotal semantics, but it does not introduce new parameter-level meaning not already in the schema. Baseline 3 is appropriate because the schema carries the parameter semantics.

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 specific verb and resource: 'Поиск извещений о госзакупках РФ' (search for Russian state procurement notices), and enumerates the supported filters (text, region, customer INN, NMCC range, period) and the returned list fields (number, name, NMCC, customer, region, dates, winner/price if awarded). This makes the tool clearly distinct from siblings like get_tender (single tender details) and search_contracts (contracts).

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 supplies clear usage context: it searches notices by text and filters, with a default period of '2y' and a warning that 'all' is noticeably slower. It also specifies quota behavior (anonymous vs free vs paid), which helps an agent decide whether to use this tool under limits. However, it does not explicitly name alternatives or state when NOT to use this tool, so it falls short of a full 5.

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