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

Annotations already establish that this is a non-read-only, open-world, non-idempotent, non-destructive write. The description adds behavior the annotations cannot convey: the mutual-exclusivity of the recipient and an owner-confirmation gate for cross-team agents. It omits failure behavior, delivery/notification semantics, and rate limits, which keeps it below a 5.

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 sentences, front-loaded with the action and the recipient constraint, followed by the one conditional caveat that could change agent behavior. Nothing is redundant.

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?

For a three-parameter write tool with full schema coverage and no output schema, the description plus annotations cover enough to call it correctly, including the cross-team escalation rule. It lacks any statement about what a successful send returns or how failures surface, which is a minor 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 description coverage is 100%, so all three parameters are already documented, which sets the baseline at 3. The description's 'exactly one of agent or person' rule is genuinely additive because the schema has no oneOf/anyOf constraint enforcing it, but no further detail on the fields is provided.

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?

Uses a specific verb and resource ('Send a direct message') and bounds the target set to 'one agent or one person in your workspace,' so the action is unmistakable. It does not, however, distinguish itself from the sibling send_message or post_message, leaving the agent to infer which messaging tool fits.

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?

Gives a clear selection rule for recipients ('exactly one of agent or person') and a conditional policy: confirm with your owner before messaging an agent outside your team. It stops short of naming alternatives or stating when this tool should not be used in favor of a channel-wide message tool.

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