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

Adds real context beyond the destructiveHint=true annotation: mutations are partial rather than full-replacement, status changes are the sanctioned removal mechanism, and the call is two-phase (status='confirmation_required' with action_id and plan_token). The claim that carriers are never deleted refines rather than contradicts destructiveHint, since suspension/archival is still a state-destroying write. It stops short of saying whether omitted fields are preserved versus cleared, which is the one gap a mutating agent would want closed.

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?

Front-loaded with the mutable surface, then constraint, then protocol. Every sentence is short and load-bearing, though 'Requires confirmation' is partially restated by the following CONFIRMATION block, costing a little redundancy.

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 11 parameters, no output schema, and thin schema coverage, the definition does well on the confirmation protocol and mutation semantics. It is still incomplete on the required carrier_id as the record selector and on organization_id scoping, leaving an agent to infer how the target record is identified.

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?

With only 18% schema description coverage across 11 parameters, the description must carry more weight. It maps semantic meaning onto roughly half the inputs (contacts→contact_person/phone, contract, edrpou, rating, status) and implies partial-update semantics, but leaves name, kind, notes, organization_id, and the required carrier_id entirely unexplained in both places.

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?

States a specific verb and resource ('Edit a carrier') and enumerates the mutable domains (contacts, contract, ЄДРПОУ, rating, status). The verb+resource pairing separates it cleanly from logistics_create_carrier and the other logistics_update_* siblings.

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?

Explicitly handles the deletion question ('Suspending or archiving is how a carrier is taken out of use; carriers are not deleted') and prescribes partial-update behavior ('Send only what changes'). It also names the follow-up path, stating the write only lands after confirm_action, which routes the agent to the right sibling.

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