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

With no annotations, the description carries the load and does disclose key behavior: ~2 minute delivery latency, a 25-wallet cap, a 1-wallet/3-day free trial, and that size filters and >1 wallet require a Pro key sourced externally. It omits lifecycle details such as how to stop alerts, whether repeated calls duplicate subscriptions, and failure behavior.

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 core behavior and latency are front-loaded in one sentence, and the second sentence packs tier limits and key provenance. The pricing/marketing framing ('Free trial... no signup... 5 USDC/month') is partly promotional, but the key and limit information is actionable.

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 5-parameter mutation-style tool with no annotations and no output schema, the description covers purpose, timing, limits, and auth but says nothing about what the call returns (subscription ID?) or how to cancel an existing alert. An agent can invoke it, but cannot reason about the resulting state.

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 40%, so the description must compensate and largely does: it establishes that 'addresses' means Hyperliquid wallets capped at 25 (1 on trial), that min_usd-style size filters are Pro-only, and that pro_key is the HW-... key from a specific URL. It still adds nothing about chat_id or how min_usd interacts with the Pro requirement.

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: 'Push every new fill of up to 25 Hyperliquid wallets to a Discord webhook or Telegram bot.' That is clearly a push-subscription tool, distinct in kind from the query siblings get_wallet_positions and get_wallet_trades, though the description never names those siblings explicitly.

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?

Usage is only implied: the tool is for real-time fill notifications rather than polling, and the trial/Pro tiers hint at when a paid key is needed. There is no explicit 'use this instead of get_wallet_trades when...' statement or guidance on what to do if a subscription already exists.

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