get_predictions_for_stop

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

The description mentions that data is real-time and never cached, which is a useful behavioral trait. However, it does not disclose other aspects like error handling or performance implications. With no annotations, the description carries the full burden but only partially satisfies it.

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?

The description is two sentences, front-loading the core function and adding a key detail about real-time nature. No unnecessary words.

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?

The description covers the main purpose and data freshness, but it lacks details on edge cases (e.g., empty result) and contains a contradiction about parameter optionality. With an output schema present, some missing details are compensated, but the contradiction hurts completeness.

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 description says 'or just the latest one if not specified' for the top parameter, but the input schema marks top as required. This contradiction misleads about parameter optionality. Schema coverage is 100%, but the description adds confusion instead of clarity.

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 clearly states the tool fetches predictions for a specific stop, and the name itself indicates the function. It distinguishes from siblings like get_routes and get_vehicle by focusing on predictions.

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 context of use is clear from the description and name, but there is no explicit mention of when not to use this tool versus alternatives. The implied usage is sufficient.

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