save_delivery_address

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

With no annotations provided, the description carries the full behavioral burden and does so effectively. It discloses that the server performs the parsing, that optional structured fields override parse results, that missing parts must never be invented, and that after success the agent should relay sayToUserRu while waiting orders resume automatically. This goes well beyond what the tool name alone implies.

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 front-loaded with the core purpose, then flows through triggers, usage, parsing behavior, constraints, and post-action behavior. Every sentence earns its place, and the detail about automatic resume and sayToUserRu would be genuinely costly for an agent to infer on its own.

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 13-parameter tool with no output schema and no annotations, the description is unusually complete. It supplies trigger conditions, input format guidance, override semantics, no-hallucination instruction, success-response behavior, and side-effect context. An agent has enough information to invoke the tool correctly and handle the outcome.

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 15%, so the description must compensate. It does this by explaining that `text` is the messy full phrase and that the server splits it into street, house, apartment, floor, entrance, intercom, and phone, while structured fields override the parse. A few self-explanatory fields like city, comment, postalCode, and recipientName are not individually discussed, but the key behavioral parameter `text` is thoroughly covered.

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 opens with a specific action, 'Save the owner's home address into the AgentPay cabinet', and adds the key detail that it is 'parsed into courier fields'. This clearly differentiates it from the sibling read tool get_delivery_address and from broader preference-update 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 description gives concrete trigger scenarios: specific Russian phrases like «сохрани адрес», dictation of apartment/entrance/intercom/phone, and the post-NEED_USER_DATA case. It also explains that the full chat phrase should be passed as `text`. It stops short of naming when not to use the tool or pointing to an alternative, so it earns a 4 rather than a 5.

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