Read a whole conversation

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

Annotations already declare this a safe, idempotent, non-destructive, closed-world read, so the description correctly spends its budget on behavior the schema cannot express: a 1,000-message snapshot cap, a five-minute expiry, and explicit truncation reporting. The expiry and cap are exactly the facts an agent needs to decide whether to restart or continue a cursor, which is high-value context beyond the hints.

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 short sentences, front-loaded with the core action and trailing with the constraints, with no filler. The terse phrasing of "only cursor=nextCursor and limit" is efficient but slightly ambiguous about whether message_id must be dropped on continuation.

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?

An output schema exists so return values need no explanation, and the snapshot lifecycle is well covered. What remains missing for a four-parameter, zero-coverage tool is the message_id versus header_message_id distinction and what happens when a cursor expires, both of which an agent needs to call this 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 order coverage is 0%, so the description carries the full burden and explains three of four parameters: message_id as the entry point, cursor as nextCursor, and limit. It leaves header_message_id completely unaddressed, which is the most confusing part of the schema given there are two identifier parameters with different types, and it omits the default limit of 100.

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 ("read a conversation oldest first") plus a scope that distinguishes it from single-message siblings: it traverses indexed folders and accounts. However, it never names an alternative such as mail_get or mail_search, so the agent must infer the difference from the name alone, and the name ("search_conversation") slightly undersells what is actually a full-thread read.

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?

"Start with one message identifier. Continue with only cursor=nextCursor and limit" is a genuine call-sequence instruction, but it only covers the pagination flow. There is no guidance on when to choose this over mail_get for a thread, or over mail_search for a query, and no stated preconditions such as whether the message must be already indexed.

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