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

Annotations cover the read-only/idempotent safety profile, and the description adds context they cannot: a per-call cost of $0.01 USDC via x402 on Solana, charged only on successful calls, plus an equivalent HTTPS endpoint. Cost and payment rail are exactly the kind of operational behavior an agent must know before invoking.

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 filter capability are front-loaded in the first sentence, followed by return fields, pricing, and the alternate endpoint. High information density with no filler.

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 13-parameter, no-output-schema tool, the description compensates by naming the returned fields (magnitude, place, time, coordinates, depth, tsunami flag, PAGER, felt reports, links) and disclosing cost/transport. Nothing material an agent needs to call it correctly is missing.

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 100%, so the baseline is 3, but the description adds value the flat 13-param schema doesn't: it groups the params into two coherent spatial modes (box vs circle) and two time modes (days vs start/end), telling the agent these are alternatives rather than independent inputs. It also previews which fields are returned without a formal output schema.

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+resource ('Recent earthquakes from the USGS') with an explicit and unique data source, and enumerates the supported filter axes (bbox, circle+radius, magnitude, time window). No sibling tool covers seismic data, so the agent can identify it instantly.

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?

The description implies the two spatial query modes (bounding box vs center point + radius) and the two time-window modes (last N days vs start/end dates), which is real selection guidance. It stops short of explicit 'use X when Y' exclusions, but there are no competing earthquake siblings to disambiguate against.

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