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

Annotations already declare readOnlyHint and openWorldHint=false, and the description adds a genuinely non-obvious side-effect guarantee: 'Reading marks nothing as read.' It also documents ordering (most recent first) and the meaning of 'unread' for the team, which go beyond the structured fields.

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: what the call returns first, then the no-mark-as-read guarantee, then pagination. It is one dense run-on sentence-chain, but nearly every clause carries information and nothing is repeated wholesale.

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 compensates by enumerating returned fields (visitor name/email, source page, last message preview, unread flag) and ordering. Combined with the read-side-effect note, an agent has enough to call it correctly; only the site_id scoping remains unexplained.

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 100%, so all three parameters are already documented; the baseline is 3. The description echoes the closed and cursor semantics ('Pass next_cursor as cursor') and never mentions site_id, so it adds little meaning beyond 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 description opens with a concrete resource framing ('The live chat inbox: ongoing conversations with visitors') and adds scope details (most recent first, closed vs ongoing). It is separable from get_conversation and list_channels without opening a schema, though it never names a sibling 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 operational guidance for pagination ('Pass next_cursor as cursor for the next page') and for the closed flag, but never states when to use this list versus get_conversation for a single thread or search_channels. Usage is implied by the 'inbox' framing rather than stated as a decision rule.

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