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

Beyond readOnlyHint=true, the description discloses the 500-per-call cap, the incremental-fetch tag contract, the remainingEvents indicator, and the important caveat that events can arrive out of order when devices were offline. That ordering caveat is behavioral context an agent cannot get from annotations or schema.

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?

Front-loaded with the core purpose, then pagination, then the ordering caveat, with the API endpoint tacked on. Dense but nearly every clause carries information; the long event-type enumeration is the only slightly padded element.

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?

No output schema exists, yet the description covers the return contract (tag to reuse, remainingEvents flag) and the ordering caveat, so an agent has everything needed for correct repeated invocation of this read tool.

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 only one parameter exists, so the baseline is 3. The description adds genuine meaning by explaining that after_tag should be the tag returned from the previous call and that it filters to newer events only — richer than the schema's terse 'tag from a previous call'.

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 ('Read driver-app events for the live routes') and enumerates the exact event types returned, which distinguishes it from the order- and route-centric siblings. An agent can tell immediately this is the event-log reader.

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 explains the pagination workflow (pass the returned tag as after_tag to get only newer events), which is usage guidance for a repeat caller, but it never states when to prefer this tool over siblings like get_routes or get_dispatch_status. Usage is implied rather than framed against alternatives.

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