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

Annotations already cover readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description adds genuinely new behavioral detail beyond the annotations: results are ordered oldest-first and 'before' pages toward older messages, which tells the agent how to paginate.

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 short sentences with zero waste; the core behavior is front-loaded before the pagination detail.

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?

For a small 3-param read tool with no output schema, the essentials (ordering, cursor meaning) are covered. However, the limit bound (max 50) and the conversation_id identifier's origin are left to the schema and inference, so it is adequate but not fully self-contained.

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 only 33%: 'limit' is documented in the schema, but 'conversation_id' and 'before' are not. The description compensates for 'before' by explaining it is an ISO 8601 cursor for older pages, but adds nothing about conversation_id, leaving a gap.

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?

States a specific verb and resource ('Returns messages in one thread') plus the ordering guarantee. It is clearly distinguishable from search_messages by implying single-thread retrieval, though it never names that 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?

No guidance on when to prefer this over search_messages, nor any prerequisites or context for use. The reader must infer the thread-reading use case from the name alone.

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