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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so the safety profile is covered. The description adds genuine behavioural context beyond that: catalogue coverage differences per agency (INGV down to about M0.5), and the fact that this source exposes low-magnitude local events the global catalogues omit. It does not mention rate limits, pagination caps or latency, which the schema partially covers instead.

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?

It is front-loaded with a memorable example question, then moves through coverage, differentiation and return fields in a logical order, all in a handful of sentences with no obvious padding. The body is a bit dense and packed into one long multi-clause passage rather than discrete points.

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 15-parameter, all-optional tool with no output schema, the description does useful work by enumerating the returned fields (event id, origin time, lat/lon/depth, magnitude and type, region, event type). What it omits is any mention of the two spatial search modes (bounding box vs. radial radius), which the agent must discover from the schema alone.

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 100% and each of the 15 parameters (limit, times, bbox, radius, magnitudes, depths, datacenter) is already documented inline, so the baseline is 3. The description's mention of agency coverage and magnitude bands gives a little extra meaning for choosing datacenter and min_magnitude, but it largely restates what the schema already says and says nothing about combining bbox vs. radius search modes.

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 clearly establishes the resource: earthquake catalogues published by regional FDSN agencies (GFZ, INGV, RESIF, KOERI), backed by a concrete example query ('What small earthquakes happened near Etna this week?'). It also differentiates from the global USGS/EMSC catalogues, but never names or contrasts the sibling tools fdsn_stations and fdsn_availability, so an agent still has to infer the division of labour among the FDSN tools.

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?

It gives a clear usage context ('small earthquakes', 'this week') and an explicit reason to prefer it over the global catalogues: these agencies list local magnitude-1-to-3 events that USGS and EMSC never publish. There are no explicit exclusions or named alternative tools, so the agent is not told when another tool would be a better fit.

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