Send a message to a phone number

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

With only an openWorldHint annotation, the description carries the burden and reveals key behavioral traits: the phone is temporarily added to contacts (required by Telegram), the contact is removed by default, and country code format is required. This goes beyond the bare annotation and gives the agent crucial side-effect awareness.

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 sentences with no wasted words. The first sentence states the core purpose, the second explains the important temporary-contact mechanism, and the third gives the phone format. Information density is high and structure is clear.

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 covers the main workflow and the most critical nuance (temporary contact). However, there is no output schema to clarify return values, and the description does not mention what the tool returns, error conditions, or required permissions. Given the tool has 8 parameters and no output schema, this is a noticeable gap, though the core mechanics are well addressed.

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 25% (2 of 8 parameters have descriptions). The description adds meaning for 'phone' (must include country code) and indirectly for 'keepContact' (removal by default), but leaves silent, lastName, parseMode, and accountId without meaningful explanation. With low coverage, the description does not sufficiently compensate for these undocumented parameters.

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 action: sending a Telegram message to a phone number. It specifies the resource (Telegram message) and the unique characteristic (identified only by phone number), which distinguishes it from sibling tools like send_message.

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 the use case: when you need to message someone using only their phone number. It does not explicitly name alternatives like send_message for peer identifiers, and offers no exclusions or when-not-to-use guidance. The context is clear but alternatives are not explicitly contrasted.

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