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

Annotations already declare readOnlyHint=true and openWorldHint=false, yet the description still adds real behavior: results are ordered newest first, entries are previews rather than full bodies, auto-replies are flagged, and filters appear to be combinable only one at a time. That last point ('one of a campaign, a contact, a broadcast, or unread only') is the most valuable disclosure but is also slightly ambiguous about whether a single filter or an exclusive filter is meant.

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?

Three short sentences, front-loaded with ordering and result shape, then filters, then the hand-off to get_reply. The phrasing 'what people wrote back' is a little chatty for a list tool but costs only a few words rather than obscuring meaning.

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, the description does its job of sketching the return shape (previews, newest-first, auto-reply markers) and the follow-up path to full content via get_reply. The remaining gap is pagination mechanics and the role of the required project_id, which an agent must infer from the schema alone.

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 description coverage is only 14%, so the description carries most of the burden, and it covers campaign_id, contact_id, broadcast_id and is_unread as filtering options and implies cursor/limit via 'page through ... newest first'. It says nothing about project_id (the sole required parameter) or about how cursor/limit interact with the preview payload, leaving some of the 7 parameters 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?

The description gives a specific verb ('page through'), a specific resource (replies / 'what people wrote back'), plus ordering and payload shape (newest first, short preview). It also distinguishes itself from the sibling get_reply, which returns full text, so an agent can tell the two apart 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?

It explicitly routes the agent to get_reply when full text is needed, and enumerates the narrowing axes (campaign, contact, broadcast, unread) so the agent knows how to scope the list. It does not say when *not* to use it versus other list_* tools (e.g. list_sends, list_email_events), so it stops short of full when/when-not coverage.

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