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

With readOnlyHint and idempotentHint already declaring the safety profile, the description adds real operational context beyond the annotations: polling cadence, the 24-hour discovery window, DEX coverage, and a 60-second plan-based delay. It stops short of describing ordering, pagination, or what fields each alert carries, so it is strong but not exhaustive.

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?

Three tight sentences, front-loaded with the resource and its thresholds, then scope, then the plan caveat. Every clause carries information an agent would otherwise have to guess.

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 read-only list tool with no output schema, the description conveys the alert categories and their trigger semantics, which is most of what's needed. Missing pieces are result ordering and how `limit` behaves when more alerts exist than requested.

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?

At 50% schema coverage, the description needs to compensate, and it does not: `limit` is never mentioned anywhere, and `since_minutes` is only obliquely referenced through the 'last 24 hours' scope statement (which does explain the 1440 max). The description adds almost no parameter-level meaning beyond what the schema already gives for one of the two params.

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 concrete resource (liquidity alerts from a sentinel polling every ~1.5s) and the exact conditions that produce them (base liquidity down 40% or 70%+ from peak, with named alert types). An agent knows precisely what comes back without opening the schema, and the tool is clearly distinct from the wallet/rating siblings.

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 description establishes scope (24h window, three named DEXes) but never says when to call this versus another tool or when not to call it. There are no relevant siblings to route to, which softens the gap, but no explicit guidance is given.

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