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

With no annotations at all, the description still discloses real operational facts: the call is free with a daily per-caller quota, and payment/authorization must travel in the MCP request headers (X-Payment, X-Payment-Tx, Bearer fg_…) rather than as parameters — a genuinely useful auth detail an agent would otherwise get wrong. What it lacks is any statement of read-only semantics, failure modes, or quota-exhaustion behavior, keeping it short of 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?

The same free-tier and parameter facts are stated three times (English lead, [zh] block, [en] block), and the Chinese loss-distribution detail is only partially mirrored in English, so the reader must reconcile duplicated and inconsistent text. The genuinely load-bearing content (payment header guidance) is buried at the very end rather than front-loaded.

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?

Because there is no output schema, the description usefully compensates by naming the returned fields (count, total/net loss, distribution, latest 3 events), and it covers the free-quota and auth model. However, with six undocumented parameters and no annotation safety profile, the definition leaves the filtering contract and failure behavior unspecified — adequate, not complete.

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 0%, so the description carries the full burden, but it only names the six parameters (protocol, chain, classification, days, min_amount, limit) — nothing the schema titles don't already say. There is no explanation of units for days, currency/basis for min_amount, what classification values are valid, or what limit defaults to, so an agent cannot use the filters precisely.

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 gives a concrete framing ('what crypto hacks happened recently') and enumerates what comes back — matched hack count, total and net loss, loss distribution by attack type, latest 3 events — so the agent knows this is a free summary snapshot of exploit events. It does not explicitly differentiate itself from the sibling exploit-alerts.hack_report, so an agent must infer that this is the lightweight tier versus a fuller report.

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 repeated 'free' framing and 'latest 3 events' cap signal a quick, low-cost triage call, and the daily quota hints at not spamming it. There is no explicit 'use this when / use hack_report when' routing, and no stated preconditions for filtering, so the agent has to guess at the boundary with the sibling.

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