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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds a genuinely important side effect the annotations miss: 'Opening it marks its notifications read, as in the app.' It also documents message ordering (newest last), the composition of the message list, and held-reply semantics.

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 dense sentences, front-loaded with the returned contents before the held-reply note and the read-marker side effect. Slightly run-on, but nearly every clause carries factual weight.

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 fully carries the burden of describing the return payload, and it also discloses the notification-read side effect and the held-message workflow, leaving nothing an agent needs to call it correctly.

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 both parameters (limit default 50, max 200; conversationId) are fully documented in the schema. The description adds no parameter-level detail such as how limit interacts with the returned message list, so the baseline 3 applies.

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 enumerates exactly what a single conversation read returns (status, assignee, tags, messages, contact, related conversations, draft), making the resource singular and distinct from the plural list_conversations sibling. It lacks an explicit verb phrase but the title and content make the read purpose unambiguous.

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 only implied: no statement of when to prefer this over list_conversations, get_contact, or read_agent_conversation. The one routing hint ('Messages marked held ... waiting for accept_held_reply or dismiss_held_reply') covers only a narrow special case rather than general selection guidance.

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