Подключить или настроить ИИ-сервис

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

The description reveals important behavioral details beyond the annotations: passed keys are appended onto existing ones, and an empty string cannot erase a key—only overwrite it. This gives the agent a concrete understanding of side effects for a non-idempotent, non-destructive mutation tool.

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 compact and well-structured: it opens with the core create/update rule, then moves to provider-specific key requirements, and closes with the merging caveat. Every sentence carries necessary information without 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?

For a complex tool with 12 parameters, a nested `credentials` object, and no output schema, the description adequately covers the trickiest aspects: the create/update distinction, per-provider credential requirements, and key-merge behavior. It does not explain return values, but this is a minor omission for a save 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 covers all 12 parameters (100% coverage), but the description adds essential semantics by explaining the `credentials` structure per provider, including required fields and the default `scope` for gigachat. This compensates for the schema's generic 'see description' note and adds value beyond schema descriptions.

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 the tool's purpose: it creates a new AI service connection when `provider` is omitted and modifies an existing one when `provider` is specified. It also distinguishes itself from sibling tools like `ai_list`, `ai_test`, and `ai_delete` by focusing on save/configure operations.

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 provides explicit conditions for use: without `provider` to create, with `provider` to update. It also lists required credentials per provider, giving concrete guidance on what inputs are needed for each service type. However, it does not explicitly mention alternative tools for reading/testing/deleting, so it lacks an explicit exclusion.

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