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

Annotations already declare readOnlyHint, destructiveHint false and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the mode is fixed for the whole connection, and test mode records without delivery. That is a non-obvious invariant an agent needs.

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 with zero filler; the returned fields are front-loaded and the mode explanation follows. Every sentence earns its place.

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 not be detailed, yet the description still names the returned fields. Combined with the send-mode semantics, an agent has enough to call this correctly; only an explicit trigger condition for when to call it is absent.

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?

The single 'context' parameter has 100% schema description coverage, including a word-count rule and a worked example, so the schema carries the semantics entirely. The description adds nothing about the parameter, which is the baseline case for high coverage.

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 (returns) and resource (connected workspace plus send mode) with the exact fields returned (id, name, slug). No sibling tool retrieves context, so an agent can immediately distinguish this as the setup/discovery call.

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?

Usage is only implied: the description explains what live vs test mode means, hinting at why an agent would call it, but never says when to call it (e.g. before sending) or what alternatives exist. With read-only siblings like messages_list this is not misleading, just under-specified.

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