query_cloudtrail

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It discloses the IAM requirement and search scoping but does not mention pagination, retry behavior, rate limits, whether the keyword field overlaps with event_name in query semantics, or what an empty result looks like. This is adequate but not rich.

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 compact and front-loaded: a one-sentence purpose followed by a permission note and a clear list of args. The arg list is concise, but the permission sentence and args list are necessary for a tool this flexible. No filler, though the identical 'Filter by' phrasing for username and resource_name is slightly repetitive.

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?

All six parameters are explained, the permission prerequisite is stated, and an output schema exists, so return values are presumably structured. It lacks guidance on which parameters are mutually exclusive or how keyword interacts with event_name, and no explicit maximum result count is stated in the description beyond the schema's limit default.

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 description coverage is 0%, but the description provides inline Arg explanations for all six parameters, including the example 'DeleteDeployment' for event_name and a range for timeframe_minutes. This compensates for the schema gap and adds semantic value beyond type/constraint information.

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 uses a clear verb ('Search') with a specific resource ('AWS CloudTrail events') and enumerates concrete filter dimensions (keyword, event name, username, resource). Although no title is provided, the description is specific enough to distinguish from sibling log-query tools like query_logs_custom or search_traces, since it names AWS CloudTrail and its IAM requirement.

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 states it 'Requires cloudtrail:LookupEvents IAM permission,' which is useful guidance for when this tool is applicable. It does not explicitly compare to sibling tools or state when not to use it, but the mention of AWS CloudTrail and IAM permission gives enough context to infer appropriate usage relative to log/metrics siblings.

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