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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds ordering and a pagination concept, which is useful, but the reference to a non-existent 'starting_after' parameter introduces inaccuracy, so it only partially adds value.

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 first sentence is concise, front-loaded, and clear. However, the second sentence, though compact, contains a factual error that reduces its value and reliability. It is not verbose, but it fails to earn its place due to misinformation.

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 presence of an output schema reduces the burden of describing return values, yet the description's pagination guidance is incomplete and incorrect: it omits the actual parameter 'ending_before' and instead names a non-existent 'starting_after'. This leaves an agent unable to correctly paginate, a significant gap for a paged-list tool.

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, but the description actually undermines parameter understanding by referencing 'starting_after' instead of the schema's 'ending_before'. It does not meaningfully explain any parameters beyond what the schema already provides, and it adds confusion.

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 states a clear action ('Read') on a specific resource ('a chat's messages') and adds an ordering detail ('oldest first'). This clearly differentiates it from sibling tools like list_chats, which list chats rather than messages.

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 gives some context (read messages, page through older ones) but provides no explicit guidance on when to choose this over list_chats or get_chat. More importantly, the pagination instruction mentions 'starting_after', a parameter that does not exist in the schema, making the guidance actively misleading.

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