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

Annotations cover the safety profile (readOnly, openWorld, non-idempotent, non-destructive), but the description adds nothing about coverage lag, refresh rate, or what a 'past moment' snapshot returns. For an open-world live-data feed with a time dimension, the behavioral burden is largely unmet.

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?

One short sentence, resource stated up front, no filler. The brevity is appropriate in form, though it comes at the cost of the missing parameter and usage detail.

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 0% schema description coverage, an untyped 'input' object, and no output schema, the description needed to carry nearly all the explanatory weight and does not. An agent cannot confidently construct the call from this definition.

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 parameter is named 'input' with an empty schema ({}), 0% coverage and no type. The description only vaguely gestures at 'a past moment' without stating that the parameter is a timestamp, its format, or whether it is optional. This is the biggest gap in the definition.

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?

It names a concrete resource (MBTA buses, subway and commuter rail) and a temporal dimension, so the agent knows roughly what data it returns. But the phrase 'now, or at a past moment' makes it indistinguishable from the sibling cell_sensor_mbta, which is presumably the current-only variant; the '_at' contract (point-in-time snapshot) is never stated explicitly.

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?

No guidance on when to pick this over cell_sensor_mbta, or over the many other cell_sensor_*_at siblings. The temporal hint is the only selection signal, and it is ambiguous rather than directive.

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