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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral guarantee — 'POAScan never solves or embeds a proof' — and discloses that the output carries combined_sha256 and template_sha256. However, most of the remaining text is remote-service protocol detail (403 required_bits, 202 pending polling rules) that belongs to the join flow rather than to how this tool behaves when invoked.

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?

The whole definition is a single sprawling sentence with nested parentheses carrying three separate sub-topics (steps, join, self_custody) and hash fields. For a zero-parameter tool returning static onboarding text, this density obscures rather than front-loads, and no structure separates what the tool returns from background domain lore.

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?

With no output schema, the description must convey the payload, and it does: canonical prompt text, numbered steps, the join flow shape, self_custody manual steps, and the combined_sha256/template_sha256 fields. Enough is present for an agent to know what a caller will receive, though the ordering of that content is hard to extract.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-argument tool applies. The description does not waste words on inputs and implicitly confirms the call needs no arguments.

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 opening clause does state the resource — the canonical prompt and numbered steps for starting PoA mining, sourced from poascan.io/start and minepoa.com/go.md. But the purpose is buried under a long parenthetical dump of endpoint semantics (GET /api/join-pow, POST /api/hosted/register, 403/202 handling), so an agent must parse a lot before confirming what it gets back. It also only glancingly differentiates from siblings via the negative 'Mining does not read swaps/status'.

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?

There is an explicit trigger: 'Use it when someone asks how to join or start earning,' plus a scoping exclusion that mining does not read swaps/status, steering away from get_swap_status/get_route_status. What is missing is naming a concrete alternative for related-but-different questions, but the when-to-use condition itself is unambiguous.

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