run_operation

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it is dangerous, may modify data, runs under a secret key, and can be disabled via an environment variable. This exceeds typical descriptions by highlighting side effects and safety mechanisms. However, it does not describe return behavior or error cases, which are inherently variable for arbitrary operations.

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 a single, short sentence that immediately conveys the danger and purpose. It is front-loaded with the warning and efficiently states both the capability and the safety toggle. No redundancy or filler.

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 an arbitrary-operation tool with no output schema and no annotations, the description covers the risk profile but omits practical guidance like how to discover operation names, what the response format looks like, or typical use cases. Given the tool's open-ended nature, some guidance would be helpful for safe invocation, but the minimal description is partially acceptable because the behavior depends entirely on the called operation.

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 schema already provides descriptions for all three parameters (operation, body, mode) with 100% coverage. The description adds no additional semantic detail beyond the schema. It does not explain how to reference operation names or provide examples. Since coverage is high, the baseline 3 is appropriate; the description does not compensate for any gaps.

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 clearly states that this tool executes an arbitrary Mindbox API operation ('выполнение ПРОИЗВОЛЬНОЙ операции Mindbox API'), which distinguishes it from the specific sibling tools like get_customer or create_order. It uses a generic verb 'run' but the arbitrariness is explicit. It doesn't specify a particular resource, but for a raw-operation tool that's appropriate.

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 implies this is for operations not covered by dedicated tools (since it's arbitrary and warns of danger), and mentions a safety toggle (MINDBOX_ALLOW_RAW). However, it does not explicitly state 'use this when no other tool fits' or provide alternatives. The warning signals caution, but when-to-use versus when-not-to-use is only implied, not stated.

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