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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds substantive context beyond that: the write publishes to a PUBLIC network (a visibility consequence), the request must be signed by the agent's own key, and that signature proves key ownership. It also frames the call as an upsert ('join or update'). What it never states is idempotency guarantees, failure modes, or whether the listing is immediately visible.

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, no filler, with the workflow step and the identifying clause front-loaded ahead of the usage restriction. The parenthetical is the only mild interruption.

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 mutating, open-world publishing tool with no output schema and 86% of parameters undocumented, the definition covers purpose, sequencing, auth premise, and the explicit-user-request gate. That leaves the meaning of five required/optional fields and the outcome of the call unexplained, which is a real gap for the schema it fronts.

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?

Seven parameters with only 14% schema description coverage (log_url alone is documented), so the description must carry the burden and it does not. It gestures at 'signature' and the signed request but never explains ts, public_key, name, homepage, or description, nor the signing scheme the required signature/ts pair implies.

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 verb pair (join or update) and a specific resource (a listing in the public AgentProof Network), and the 'Step 2' marker situates it in a workflow, implicitly following network_join_message. It never names a sibling outright, so differentiation is inferred rather than stated.

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 gives an explicit gating rule — 'Only use when the user explicitly asks to list their agent publicly' — which is a real precondition plus an exclusion for all other cases. It does not name an alternative tool for the non-public cases, but the 'Step 2' framing makes the prerequisite step evident.

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