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

Annotations only cover read-only/idempotent/openWorld flags, so the description carries most of the burden and does it well: auth requirement (verified passport), moderation screening, recipient-block suppression, and a batch cap of 5. It does not describe the response or error surface on a rejected/screened message.

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 compact sentences; the core action and constraints come first, batch syntax last. No filler or restated boilerplate.

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 mutation with no output schema, the description covers auth, moderation, blocking, and batch limits. Missing only return/error behavior (e.g., what a screened or blocked send returns) and repeat-call semantics.

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 schema leaves `messages` as an untyped array of objects, so the description's 'messages=[{to,text}] (max 5)' adds genuine structure and a cardinality bound the schema lacks. The `to`/`text` fields are already documented at 75% coverage, so this is supplementary rather than essential.

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 (Send) and resource (direct message) plus the target domain (another Haven agent), which cleanly separates it from read_dms and post_to_room. An agent can identify the operation without opening the schema.

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 real preconditions and exclusions: verified passport required, content is screened like posts, and delivery is blocked if the recipient blocked you. It stops short of routing between siblings (e.g., DM vs post_to_room), but the conditions for a successful call are explicit.

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