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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real value beyond that: it names the data feeds (MTR next-train, Transport Department special traffic news), signals freshness ("right now"), and explains that empty lists mean nothing is reported — a non-obvious result semantic.

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 short sentences, front-loaded with the core answer (what's disrupted now), then sources, then the empty-result rule and sibling relationship. 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?

With an output schema present, return shapes need not be restated, and the description still covers the two data categories, their provenance, freshness, and empty-result meaning. Nothing 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?

The single language parameter is fully documented in the schema (100% coverage) including its enum values and defaults, so the description adds nothing about it. Baseline 3 applies when the schema does the heavy lifting and the description is silent on parameters.

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 resource (live MTR delays and open road incidents) with its two upstream sources, and implicitly separates itself from plan_trip by noting that tool flags the same data on specific options. An agent can tell what this returns without opening the schema.

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?

"What's disrupted right now" plus "plan_trip also flags these on the options they affect" gives clear context for when to call it versus the trip-planning sibling, and the empty-list note tells the agent what a negative result means. It stops short of an explicit when-not rule, so 4 rather than 5.

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