direct_call

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

With no annotations, the description must carry the behavioral burden, but it only states the HTTP mechanics and broad scope. It does not warn that this universal call can mutate or destroy production data (delete, archive, suspend are possible), nor mention sandboxing, auth needs, or side effects. 'Покрывает всё управление' hints at writes but does not disclose consequences.

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?

Three dense sentences with no filler. The first sentence front-loads the core call pattern, the second scopes what it covers, and the third gives a direct pointer to the reference tool. Every sentence earns its place.

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?

The description is serviceable for a generic wrapper: it names the endpoint shape, scope, and prerequisite reference. But with no annotations or output schema, it omits auth context, sandbox behavior, and any statement about the raw response shape; those are left to schema fields, which is a noticeable gap for a tool that can perform destructive operations.

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 coverage is 100%, so the baseline is 3. The description adds real semantic value by showing how parameters map to the request structure: service goes into the URL path and method/params form the JSON body. It also tells the agent where to find valid service/method names, though sandbox and client_login are left to the schema.

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 is explicit: 'Универсальный вызов Яндекс Директ API v5' followed by the exact HTTP action 'POST на /json/v5/{service} с телом {method, params}'. It lists the covered resource domains (campaigns, adgroups, ads, keywords, bids, retargeting, dictionaries), which clarifies scope and distinguishes it from the more specialized sibling tools.

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 phrase 'Сначала загляни в direct_reference за именами сервисов, методов и формой params' gives a concrete prerequisite and points to an alternative tool. It clearly establishes direct_call as the universal management entry point, though it does not explicitly state when to prefer direct_status or direct_report.

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