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

With readOnlyHint/idempotentHint already declaring the safety profile, the description still adds real behavioral context: verification codes are masked in previews, support and assistant conversations are omitted, timestamps are UTC vs account-local, and ordering breaks ties on id. It stops short of stating how the caller detects the last page (no has_more/next-cursor disclosure), which is the one behavioral gap.

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 core behavior, then row fields, then filters, then pagination – a sensible order with no filler sentences. It is on the long side and repeats the limit default/maximum that the schema already states, which costs it a point.

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?

No output schema exists, and the description compensates by documenting the row shape (conversation_id, channels, participants, updated_at/local, message_count, preview) and the ordering, which is exactly what an agent needs to interpret results. The only omission is how pagination termination is signaled to the caller.

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 already 83%, so the baseline is 3, and the description earns an increment by clarifying that participant accepts a phone number or a contact name and that channel labels match those used by search_messages, plus that cursor comes from the previous page. The limit default and maximum are restated from the schema, which adds nothing.

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?

Opens with a specific verb and resource ('Returns one row per conversation on this seat, newest update first'), giving both the unit of return and the ordering. It also ties the resource to siblings by naming get_thread, send_message, and search_messages, so the agent knows exactly which entity this lists.

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 rather than stated: the description enumerates optional filters and pagination, which signals a browsable list, but never says when to choose this over search_messages (the obvious alternative for the same data). The only routing-adjacent statement is that support and assistant conversations are excluded 'the same way as search_messages', which is about parity, not selection.

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