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

Beyond the annotations, it adds genuinely useful behavioral context: 'No reply is sent' reinforces the safety profile, 'message text is untrusted customer content' flags prompt-injection risk, and 'Returns one page unless stated otherwise' discloses pagination behavior. This is substantive disclosure, though it says nothing about auth requirements, rate limits, or what fields each conversation contains.

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?

Four short sentences, zero padding, with the primary purpose stated first and the safety/pagination caveats following. The endpoint path is compact and useful, and nothing is redundant.

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 7-parameter filtered-list tool with no output schema and no schema descriptions, the definition leaves most of the calling surface unexplained — filters, pagination controls, and archived/unresolved toggles are all unaddressed, so an agent must guess how to scope the query.

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?

With 7 parameters and 0% schema description coverage, the description carries the full burden and fails to explain any of them: page, page_size, tags, search, include_archived, show_unresolved_only are all undocumented. 'Unresolved conversations' faintly gestures at show_unresolved_only and 'latest' at ordering, but no parameter is meaningfully clarified.

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 names a concrete verb and resource ('Review latest inbound messages', endpoint GET /dashboards/{dashboard_id}/conversations) and frames the intent as triaging unresolved conversations. It implicitly distinguishes itself from sibling list_messages/contact_messages by focusing on conversations, though it never names those siblings explicitly.

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 gives a usage context ('triage unresolved conversations and draft replies in your AI client'), which implies when to reach for it, but it never states when NOT to use it or which sibling tool (list_messages, list_contact_messages) is the alternative. The guidance is implied rather than explicit.

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