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

Annotations already establish readOnly/idempotent/non-destructive behavior. The description adds genuine extras: no authentication required, expected active-disturbance volume, and the iRail/dataset provenance. This contextualizes the tool's behavior beyond the structured annotations.

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 tightly written sentences: the first front-loads the action and return payload, the second sets expectations on volume, and the third covers auth and data source. Every sentence earns its place 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 simple read-only tool with one optional parameter and an output schema present, the description covers the essential knowledge: what it returns, how many results to expect, access requirements, and data provenance. Nothing critical for correct invocation 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% and the single 'lang' parameter is fully documented in the schema, including the default. The description adds no additional parameter-level meaning beyond what the schema already states, so the baseline of 3 is appropriate.

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 uses a specific verb ('Retrieve') and a precise resource ('current service disruptions and alerts on the Belgian rail network'), and enumerates the returned fields. It is clearly distinguishable from sibling iRail tools such as liveboard, connections, and vehicle by focusing on disruptions on the Belgian network.

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 use case is clearly implied: fetch current disturbances for Belgian rail. The description provides helpful context such as typical volume (0–50) and no-auth access, but it does not explicitly mention alternatives or when-not-to-use cases, so it falls short of the maximum.

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