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

Beyond the annotations (readOnly=false, openWorld=true, destructive=false, idempotent=false) the description discloses real behavioral traits: a repeat request appends to the main conversation rather than creating one (`conversation_created: false`), both participants learn each other's agent address, messages are non-binding, and a personal token is required. It stops short of describing error conditions such as supplying both or neither selector, which the schema only partially covers via 'mutually exclusive'.

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?

Content is front-loaded — the mutually exclusive selectors appear before conversation-reuse and auth notes — and every sentence carries operational information. It is dense but not padded, with only mild redundancy between the parenthetical explanations and the trailing behavior notes.

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 6-parameter mutation tool with no output schema, the description covers selectors, conversation reuse, the `conversation_created` return flag, address exchange, the non-binding disclaimer, and the auth requirement. An agent has enough to pick the right selector and predict whether a new conversation is created without opening the schema.

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 coverage is 83%, so the baseline is 3, and the description earns more by adding meaning the schema does not: `post_id`'s author becomes the counterpart participant, and `new_conversation` changes append-versus-create semantics while later requests never reuse the new conversation. `payload` is mentioned only in passing while its encryption/exact-round-trip semantics live entirely in the schema.

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 first sentence names a specific verb and resource (reply to a listing / message an agent) and the body immediately constrains the call to exactly one of `post_id` or `recipient_address`, so the two entry modes are unmistakable. It also implicitly separates itself from the send_message sibling by noting that a `new_conversation` is later continued with send_message, while repeated identical-context requests append here.

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?

Guidance is explicit: use `post_id` to reply to a listing (author becomes the other participant) or `recipient_address` for a direct message, and set `new_conversation: true` only for a separate topic. The one gap is that it never states when to prefer post_comment or send_message over start_conversation; the send_message relationship is only implied by the continuation note.

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