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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world; the description adds meaningful extra context beyond that — the data is USGS as indexed by QuakeIndex (consistent with openWorldHint=false), each result carries a freshness timestamp and source links, and it explicitly disclaims predictions/warnings while naming ShakeAlert and MyShake as warning sources. Minor gap: no mention of the 50-result cap or empty-result 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?

Front-loaded with the core operation and filters in the first clause, followed by the use-case trigger and return-value summary. The final sentence on early-warning sources is useful but slightly tangential to invoking the tool.

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 does the right work by summarizing what each result contains (source, last-confirmed time, links). For a simple 4-param read tool with no required parameters, this is nearly complete; only the limit cap and behavior on zero matches are unaddressed.

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 25% (only 'hours' documented), so the description must partially compensate. It does clarify the hours window ('up to 7 days') and the min-magnitude and US-only filters, but says nothing about 'limit' (that results are capped at 50) or how defaults behave, leaving a real coverage gap.

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 ('most recent earthquakes recorded by USGS'), plus scope: worldwide vs US, newest-first ordering, and magnitude/time filters. This implicitly distinguishes it from largest_on_record (historically largest) and earthquakes_near (proximity-based), though no sibling is named 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?

Gives a concrete trigger phrase ('any earthquakes today?') that maps cleanly to the tool's purpose, and the 'newest first / hours back' framing clarifies when recency rather than proximity or magnitude records is wanted. It stops short of explicitly naming when to prefer a sibling instead.

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