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

Annotations already cover safety (readOnly, idempotent, non-destructive, non-openWorld), and the description adds real behavior beyond them: default to all platforms, newest-first ordering, exactly which fields each item carries, null semantics for customer linkage, how hints are computed (words found in the message), and the caveat that hints are heuristic. It does not mention pagination or any cap behavior for `limit`.

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 the filter and ordering, then the item shape, then the hint caveat. The field enumeration is dense but earns its place given no output schema. Minor waste in the inline line break and the unrelated 'answer in the language of the message' instruction.

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?

There is no output schema, so the description carries the return shape itself and does so field by field, including nullability. With annotations covering safety and three of four parameters explained, an agent has everything needed to call it and interpret the result; only `limit` semantics are 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?

Schema coverage is 0%, so the description must compensate and largely does: `days` is defined as the recency window on the customer's last message, `platforms` enumerates the allowed codes and states the default-all behavior, and `only_hinted` is defined as keeping items with any hint. Only `limit` is left entirely unexplained.

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?

States a specific verb and resource with tight scope: conversations whose last message came from the customer within `days`, newest first, across ig|fb|tw|wp. The 'sales signals' idea is made concrete through the returned hints (quote/accept/reject), so an agent can tell it apart from plain listings like list_chats. It stops short of naming the sibling it displaces (list_chats, chats_collect_complaints).

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?

Usage is implied by the sales-signal framing and the `only_hinted` explanation, plus the explicit instruction to read the message and decide rather than trust hints blindly. There is no explicit when-to-use / when-not / use-instead-of guidance relative to list_chats or chats_collect_complaints.

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