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

The description adds useful behavioral context beyond the readOnlyHint and idempotentHint annotations: oldest-first ordering and tail-based paging. However, it instructs callers to 'page back through older ones with starting_after,' which directly contradicts the schema where the actual paging parameter is ending_before. This misleading behavior guidance is a significant flaw.

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 short and front-loaded with the core purpose, which is good. However, the second clause introducing starting_after is inaccurate and does not earn its place, undermining what would otherwise be a concise, well-structured one-liner.

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?

Annotations and the output schema cover safety and return values, and the schema documents ending_before well. However, the description's incorrect pagination instruction leaves the agent without reliable guidance for the exact workflow it claims to explain—reading older pages. For a paginated read tool, this is a material completeness gap.

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 the baseline is 3, and the description does add semantics around limit ('most recent limit messages'). Yet it names starting_after, which is not present in the schema, and never references the real ending_before parameter. The parameter guidance is therefore actively misleading rather than additive.

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 specific verb and resource: 'Read a chat's messages, oldest first.' This clearly distinguishes it from siblings like list_chats, get_chat, and send_message. The core purpose is unambiguous despite later pagination wording issues.

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 implies the tool is for reading a chat's message history and gives ordering/pagination context. However, it does not explicitly state when to prefer this over siblings like list_chats or get_chat, and the pagination advice names a parameter that does not exist in the schema.

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