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

Annotations already cover read-only and non-destructive behavior, so the description's job is to add operational context — and it does: NJT needs credentials configured, and PATH alerts are returned as explicitly unavailable rather than fabricated, which is important for interpreting results correctly. It stops short of describing rate limits or freshness/caching of alert data.

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?

Two sentences with no filler in the parenthetical caveats, but the leading "Service alerts." duplicates the title and burns the highest-value position on a restatement rather than on what the tool does. The dense credential/PATH caveat is packed into one overlong sentence.

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?

An output schema exists, so return-value detail is not needed, and the credential and PATH-unavailable caveats cover the main failure modes. What's missing is the parameter's value space and a plain statement of what an 'alert' record contains — enough gaps that an agent could call it but might not know what to pass for 'system'.

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 'system' parameter has 0% schema description coverage and no enum, so the description must carry the load. It names systems in prose but never ties them to the parameter, never states the accepted values (e.g., njt/path/all) despite the 'all' default, and never says whether unknown values error out.

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 opens by restating the title ("Service alerts") and never states a verb or what the tool actually returns for a given system. It does narrow scope by naming the two systems (NJ Transit, PATH) and their coverage differences, but an agent must infer that this fetches current disruption notices rather than, say, configuring alerts.

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 NJT credential prerequisite and the pointer to server_status for enabling it give genuine when-to-use context. However, there is no guidance on when to choose this over siblings like lines, next_departures, or trip_between, and no statement of when this tool should be skipped entirely.

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