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

The description complements the destructiveHint annotation by explaining that dangerous methods require allow_dangerous=true, and discloses success/error return behavior. It also points to full documentation for deeper context, though it could elaborate on what 'normalized error' means.

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 front-load the core purpose, then address safety and results, and finish with a documentation link. No wasted words; succinct and well-structured.

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?

Given the tool's complexity, the presence of an output schema, and annotations, the description sufficiently covers the main usage scenarios and danger gating. The documentation link compensates for any missing details, though a brief example or note on normalization would make it fully complete.

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 already provides comprehensive descriptions for all four parameters, including the discriminator convention for nested TL objects. The description adds only minimal value beyond the schema, mainly reinforcing the allow_dangerous behavior, so the baseline of 3 applies.

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 is a low-level Telegram API (MTProto) invocation tool for methods not wrapped by other tools, which separates it from siblings like send_message or get_messages. The verb 'invoke' and resource 'MTProto' are specific and unambiguous.

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 to use this tool for methods not covered by other tools, providing clear guidance on when to invoke it versus using wrapped alternatives. The danger caveat about allow_dangerous=true adds practical usage direction.

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