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

Annotations already declare readOnlyHint, openWorldHint=false and destructiveHint=false, so the 'Read-only.' sentence is largely redundant. However, the description adds genuinely new behavior beyond annotations: the returned field set (name, kind, ЄДРПОУ, contact, contract, status, rating) and the response envelope {items, total, has_more}, which matters because there is no output schema. Pagination behavior is only hinted at via has_more rather than explained.

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?

Two tight sentences, front-loaded with the resource and scope, followed by filters and return shape. The parenthetical Ukrainian term and the field enumeration both carry information rather than padding. Slightly dense with em-dash-separated lists but no wasted wording.

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 usefully supplies the return envelope and record fields, and it names the filterable parameters for a five-parameter tool. The remaining gap is the undocumented limit/offset pagination contract, which an agent must infer from the schema's bounds alone.

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 only 40%, and the description compensates partially by naming the three filter parameters 'status', 'kind' and 'q'. It does not explain what 'q' searches (name? ЄДРПОУ? contact?), nor does it mention the 'limit'/'offset' pagination parameters at all, leaving two of five parameters undocumented in both schema and description.

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 gives a specific verb plus resource ('List carriers') and defines the entity's scope ('own fleet and hired subcontractors'), then enumerates the record fields. This makes the tool's output unambiguous without opening the schema. It stops short of naming a sibling (e.g. logistics_list_fleet or logistics_list_drivers) for contrast, so sibling differentiation is only implicit.

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?

It states which fields can be filtered ('status', 'kind' or 'q'), which implies a filtered-list usage pattern, but never says when to prefer this over logistics_list_fleet, logistics_list_drivers or logistics_get_* lookups. There are no prerequisites, exclusions, or alternative-naming sentences, so routing must be inferred from the noun 'carriers'.

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