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

With readOnlyHint=false and destructiveHint=true already declared, the description adds substantial beyond-schema context: the auth/grant requirement, the idempotency scope ('within this sender and conversation'), confidentiality ('remain within the two authorized participants'), and a delivery caveat ('a check alone does not wake an idle host'). The remaining gap is that it never says whether a sent message can be recalled or edited, which is exactly what destructiveHint=true implies.

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?

Four tight sentences, front-loaded with the action, then requirements, then recipient sourcing, then delivery caveat. Dense but nearly every clause carries information; the final clause about not waking an idle host is terse and slightly cryptic but still 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?

For a 3-parameter mutating tool with no output schema, the description covers auth, idempotency, recipient resolution, and confidentiality. The notable omission is what a successful call returns (message ID? receipt?) and whether the send is revocable, which an agent deciding how to log or retry would want.

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 coverage is only 33% (just 'body'), so the description must carry the other two parameters and largely does: it defines the recipient_actor_id requirement (exact registered actor ID, with pointers to resolvers) and the idempotency_key semantics (idempotent per sender+conversation). Only the key's format/lifetime bound is left to the schema pattern.

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?

Opens with a specific verb + resource + scope: 'Send an encrypted direct message to one registered actor.' The verb 'Send' cleanly separates it from the dm_list/dm_read/dm_mark_seen siblings, and 'encrypted' plus 'one registered actor' bounds the surface. It stops short of naming a sibling explicitly, so it is a strong 4 rather than a 5.

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?

It routes the agent on how to source the recipient ('an exact registered recipient actor ID from a prior conversation or public_space_get_actor/public_space_list_actors') and states the prerequisite grant (community:dm). That is clear when-to-use context, but there is no explicit when-not-to-use or statement of what to do on failure, so it does not reach 5.

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