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

Annotations only flag readOnlyHint=false and destructiveHint=false; the description adds substantial context beyond that: the exact return payload, the auth requirement (Proof account plus client authentication), and the non-obvious client behavior that the user does not see tool results. This is exactly the behavioral disclosure annotations cannot carry.

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?

Front-loaded with purpose and return values, then action sequence, then the user-visibility caveat, then access. Dense and mostly waste-free, though the three-paragraph layout is longer than strictly necessary and the ACCESS block is somewhat bolted on.

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?

With no output schema present, the description fully compensates by explaining the returned fields, the polling follow-up, and the authentication prerequisite. Nothing an agent needs to invoke and sequence this tool correctly is missing.

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 tool takes zero parameters, so the baseline is 4. The description usefully documents the return shape (deep_link, qr_code, qr_text) even though there are no inputs to disambiguate.

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?

Names a specific verb and resource ('Create a Telegram chat ID discovery token') and immediately states what it returns (deep_link, qr_code, qr_text) and why (reveals the user's chat ID for HITL config). An agent can distinguish this from siblings like create_hitl or poll_chat_id_discovery without opening a 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?

Gives an explicit chain: pass deep_link to render_auth_link, never feed qr_text to a link renderer, then poll poll_chat_id_discovery until chat_id appears, then use that chat_id in a HITL config. It names both the downstream tool and the follow-up tool, plus the pitfall to avoid.

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