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

Annotations already cover readOnly/destructive, but the description adds genuinely new behavior: messages come back in order, metadata is always present, and bodies are conditionally withheld unless agent_name holds read_body on that connection. That permission-gating is exactly the kind of context annotations cannot convey. 'Read-only' merely restates the annotation, which costs nothing but adds nothing.

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 tight sentences: return shape first, then the decision rule motivating the call. Every clause earns its place, including the memorable 'a snippet is not the message' framing.

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?

Output schema exists, so return values need no prose, and the description still explains ordering and the body-redaction condition — the two things the schema cannot. It does not state that no parameters are required or how threadId is obtained, a small gap for a 4-parameter 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 description coverage is only 25%, so the description must carry weight; it explains agentName only indirectly via its read_body permission effect and never characterizes threadId, companyId, or the nested connectionId wrapper. It adds real semantics for one of four parameters, leaving the rest to a thin schema.

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 one mail thread's messages in order') and adds scope detail (metadata first, bodies gated). It implicitly distinguishes itself from message-search siblings via 'a snippet is not the message', but never names an alternative tool, so it stops short of full sibling differentiation.

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?

Explicitly tells the agent when to use it: read the thread before proposing a stage or drafting a reply. The contrast with snippet-level search results is implied rather than naming search_connected_messages directly, so the routing guidance is clear but not exhaustive.

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