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

The annotations already mark this as read-only and open-world, and the description adds important behavioral detail: bus-stop arrivals are fetched on demand from the official source, and on LIVE failure the agent must use only estimated_eta and label it ESTIMATED, never serving stale cached arrivals. This is consistent with idempotentHint=false.

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 definition is dense but each sentence carries functional content: scope, prerequisite, special source handling, and failure policy. It is front-loaded with the main purpose, though the long final sentence mixes condition and prohibition and is a bit heavier than necessary.

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?

For a tool with no output schema, the description gives useful invocation guidance but leaves gaps: it doesn't define the response shape for the different entity types, clarify whether the LIVE/estimated fallback applies to non-bus-stop entities, or disambiguate against overlapping siblings like parking_availability, next_departures, and beach_conditions.

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 entity_id parameter is already fully documented in the schema, so the baseline is met. The description adds extra semantic detail by highlighting the bus-stop:<code> variant and underlining that the ID must come from resolve_entity. It does not, however, document return fields beyond the estimated_eta mention.

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 returns the current state of an already-identified entity and enumerates concrete examples: parking spaces, bus arrivals, tram departures, and beach flag. It lacks explicit sibling differentiation, since parking_availability, next_departures, and beach_conditions overlap with these cases, so an agent must infer which entry point to choose.

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 gives a concrete precondition: requires an entity_id returned by resolve_entity. It also specifies special handling for bus-stop IDs and a fallback rule. However, it does not state when to prefer get_current_state over the specialized sibling tools or when not to use it.

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