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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, and the description adds the parts annotations cannot: the tool never generates or holds keys, the caller signs locally, and the relay observes sender/recipient DIDs and timing. That privacy disclosure plus the discovery path is exactly the kind of context that helps an agent decide whether to call it.

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?

Purpose and return shape are front-loaded, and the empty-object discovery tip follows immediately. The paragraph is dense and heavy with protocol vocabulary, but no sentence is filler.

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 tool with no output schema, the description covers outcome, privacy exposure, key handling, and a bootstrap path — enough for an agent to call it safely. The one real omission is the meaning of the four cryptographic parameters, which is the gap the next sentence should have closed.

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% — raw_body and timestamp are documented in the schema, but did, pow, nonce, and signature carry no explanation anywhere. The description implies a signed request but never explains what pow or nonce are for, how they are produced, or that all six are optional for the discovery call, so it does not compensate for the coverage gap on a 6-parameter tool.

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?

The description names a specific action (forward a locally signed POST /v1/agents/start) and the concrete result (a relay identity, a receive-first inbox, and one starter watch), which is far more than the bare tool name conveys. It doesn't explicitly contrast itself with the similarly named voidly_join sibling, leaving that differentiation to inference.

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?

'Call with {} first for the exact protocol and a runnable Node example' gives a concrete first-call pattern an agent can act on immediately, which is unusual and helpful. It stops short of stating when this tool is preferred over voidly_join or the other voidly_* onboarding siblings.

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