search_port_events_by_vessel

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

There are no annotations provided, so the description carries the full burden. The description adds the crucial behavior about the 2-hour default window, which is not exposed elsewhere in the schema (the schema only says 'without it the service returns only the last 2 hours' in timeFrom, but that is part of schema). The description also states 'Covers only the last 2 hours unless timeFrom is given' which reinforces that. However, it does not disclose other behaviors like pagination, rate limits, whether the search supports partial matching, or if it might be slow. Given the schema already mentions the time window in the timeFrom parameter description, the description adds little beyond that; it repeats the schema's info. With no annotations, a score of 3 is appropriate because it adds some context (emphasizing the default window) but lacks deeper behavioral disclosure such as ordering, filtering, or error cases.

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 one sentence, but it's front-loaded with the core purpose and then adds a critical qualifier about the time window. It's efficient with no waste. However, it might have been more structured with a second sentence on usage context, but given its brevity, it's well-organized. It earns a 4 because it is concise but slightly dense; it could have been split for clarity, but it's not a problem.

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?

Given the tool's moderate complexity (5 params, 1 required), the description is sufficient for basic usage but lacks some completeness. It tells the agent the basic action and the time default, but it doesn't specify the output structure (no output schema), nor does it mention if there are any prerequisites (e.g., requiring a valid vessel name) or any limitations like only covering certain types of port events. With no output schema, a description of return value would be valuable but is absent. The schema covers parameters well, but the tool's behavior around the search (e.g., does it return events in chronological order? Does it support wildcard?) is missing. So 3 is fair.

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%, so the schema already describes all five parameters: vesselName, timeFrom, timeTo, limit, nextToken. The description adds minimal parameter semantics beyond what's in the schema; it highlights the timeFrom dependency for extending beyond 2 hours, but that is also in the schema. It doesn't explain the relationship between timeFrom and timeTo or how pagination works, but the schema covers that. With full schema coverage, the baseline is 3, and the description offers no extra depth about parameter usage, so 3 is correct.

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's function: 'Search port events by vessel name.' The verb 'search' specifies the action, the resource 'port events' is specified, and the parameter 'vessel name' distinguishes it from the sibling tools like 'get_port_events_by_vessel' (which may imply a different retrieval mode) and 'search_vessels' (which searches for vessel details). It uniquely targets port events filtered by vessel name, which is not covered by other siblings such as 'get_vessel' or 'get_port_events'.

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 implies usage for searching port events filtered by vessel name, and it provides a significant usage context: the default time window is only the last 2 hours unless 'timeFrom' is provided. This guides the agent on when to use it (e.g., for recent events or specific time range with timeFrom) and implicitly contrasts with tools like 'get_vessel_last_port_event' or 'get_port_inbound' that might retrieve specific events. However, it doesn't explicitly mention when not to use it or list alternatives, but the time window caveat is very useful for selection.

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