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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral value beyond that: ordering semantics ('newest first' for the list, 'oldest first' for messages) and the important fact that 'reading doesn't clear the person's unread.' It does not mention pagination or list-size limits.

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?

Two dense sentences with zero filler. The identity/scope constraint is front-loaded, then the two modes are laid out in parallel structure, making it scannable and appropriately sized for a single-parameter tool.

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 an output schema present, return-value detail is not the description's burden, and annotations cover safety. Identity scoping, both entry modes, and ordering are all present. The only real omission is how a very long list is bounded (paging or truncation), which is not addressed anywhere in the visible fields.

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% and the schema already explains the 'pro_… id from the list' format, so the baseline is 3. The description goes further by defining the semantic consequence of the parameter's presence or absence — list mode versus message mode — which is meaning the schema does not convey.

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 the specific resource (the person's professional inbox) and delimits it sharply: 'ONLY their professional conversations (recruiters, companies, their public network), never their private chats.' That negative scoping is exactly what separates it from siblings like list_conversations and read_conversation, and it also spells out both operational modes (list vs. single conversation).

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 clearly states the conditional usage: omit conversationId to get the list, supply it to get that conversation's messages. That covers when to use each mode. It stops short of explicitly naming which sibling to use for private chats, so the alternative routing is implied rather than stated.

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