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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new operational facts—a TAOSTATS_API_KEY is required, calls cost $0.003 USDC via x402 on Base/Solana/Arc, and failed calls are not charged. Those auth and billing details materially affect whether an agent should invoke it. The return-field listing partly duplicates the output schema, which keeps it from a 5.

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 returned fields come first, then sibling routing, then auth and pricing. Each sentence carries a distinct fact—no filler—and the alternative-tool clause is condensed into a single readable list.

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 an output schema present, the description needn't explain return values, and it still covers scope, auth, cost, and sibling routing. The only shortfall is that it never mentions pagination limits or default ordering, which matters for a 'recent events' feed with page/limit parameters.

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 description coverage is 100%, so page, limit, and netuid are already documented with defaults and bounds. The description only implies netuid via 'for a specified subnet' and says nothing about pagination or page-size tradeoffs. Baseline 3 is appropriate when the schema carries the parameter burden.

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 and resource—recent neuron registration events—plus scope (all subnets or a single subnet) and the payload fields returned (burn cost in TAO, netuid, uid, hotkey, coldkey). It also names the two closest sibling event tools, so an agent can separate it from crypto_subtensor_events and crypto_subtensor_block_events without opening any 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 explicit routing guidance for the event-family siblings: use crypto_subtensor_events for general Subtensor chain events and crypto_subtensor_block_events for single-block event pulls. The 'all subnets or a specified subnet' phrasing implies the netuid filter's role. It stops short of contrasting with other TAO-adjacent siblings like crypto_tao_registration_cost or crypto_tao_subnet_metagraph, so it is clear but not exhaustive.

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