login_send_code

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

There are no annotations, so the description carries the disclosure burden. It does reveal the primary side effect — Telegram will send a code — and that this is an initiating step rather than a completed login. It does not mention rate limits, code expiration, or the fact that repeated calls may invalidate previous codes, but the core behavior is disclosed.

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?

Two short sentences contain all necessary information: purpose, parameter format, example, and next step. There is no filler or redundant restating of the tool name.

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 simple single-parameter login step with an output schema present, the description is complete. It tells the agent what happens, how to format the input, and what to call next, which is everything needed to invoke this tool correctly.

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 input schema only says 'phone' is a string. The description adds essential semantic meaning: the phone must be in international format and gives a concrete example (+79991234567). This fully compensates for the otherwise absent schema-level description.

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 states a specific verb-resource pair: it is the first step of phone-number login that makes Telegram send a code. This clearly distinguishes it from login_complete and login_qr, which are the natural siblings, without needing to inspect the schema.

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 explicitly says this is the first step and instructs the agent to call login_complete(code=...) next. This is clear when-to-use guidance within the phone login flow, though it does not explicitly contrast with login_qr or explain when phone login is preferable.

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