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

The readOnlyHint annotation already indicates no mutation, and the description adds specific value beyond it by stating that read state is not changed and by directing the agent to call mark_read afterward. It also discloses the oldest-first ordering behavior, which is useful and not present in structured annotations.

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?

The description is two short sentences with no filler. The core behavior is front-loaded, and the critical follow-up action is stated immediately afterward. Every phrase earns its place.

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?

The description covers the core invocation and the mark_read follow-up, which is good. However, pagination through limit and cursor is not mentioned, order behavior is only implied, and there is no output schema to describe return values. This leaves gaps for agents needing to retrieve large threads or handle multi-page results.

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 0%, so the description must compensate, but it only explains the thread context and default ordering. It does not clarify limit, cursor, or order parameter semantics, leaving the agent to guess how pagination works or how to switch ordering.

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 clearly identifies the resource (messages in a thread) and the operation (read) through the tool name and title, and it specifically contrasts with mark_read by stating it marks nothing as read. The scope is unambiguous and easily distinguished from sibling tools like send_message or inbox.

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?

The description provides clear usage context: fetch messages in a thread and then explicitly call mark_read afterward if read state needs updating. It does not explicitly name alternatives or state when not to use the tool, but the sequencing guidance is actionable and sufficient for most cases.

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