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

Annotations only carry readOnlyHint=true, and the description adds substantial behavior beyond it: the split fields mnn, tradeName, manufacturer, and country are empty in the response because everything is flattened into name; contract number, customer, supplier, and region are absent for more than half of rows by 2026; the response includes Aggregates (total sum and quantity, number of contracts and suppliers); and the access failure mode is an explicit refusal. No contradiction with the readOnly annotation.

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 rather than short, but every sentence earns its place: search scope, data-model quirk, unsafe-filter warning, response aggregates, and access prerequisite. The verb+resource is front-loaded, and the length is justified for a 9-parameter tool with no output schema, 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?

For a 9-parameter tool with no output schema, the description covers the essential operational facts: what is searched, the response shape (flattened name field, empty split fields, Aggregates), which filters are unsafe, and the access requirement. It omits empty-result behavior and sorting, but an agent has enough information to call the tool correctly.

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 100%, so the baseline is 3. The description adds value beyond the schema by warning that filters such as customerInns, supplierInns, regionCodes, and query (contract number/customer/supplier) will silently cut off matching rows because those attributes are often missing — behavioral semantics that the parameter descriptions alone cannot convey.

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 precise verb+resource — 'Поиск по строкам спецификаций заключённых контрактов 44-ФЗ' — and defines the unusual data model: one row equals one specification position with the full text in the name field. The scope is clear, but it does not explicitly name or contrast any sibling tool (e.g., search_contract_products), so differentiation among the many sibling search tools is implied rather than stated.

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 concrete usage context: filters on contract number, customer, supplier, and region 'отсекают остальные' because these attributes are missing from most rows, and it warns that the tool depends on a KRA SOFT manager-connected MCP service, otherwise 'инструмент вернёт отказ'. This is clear when/when-not guidance for filters and prerequisites, though it never names an alternative tool, leaving when-to-pick-this-over-siblings implicit.

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