resolve_variable

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

No annotations are provided, so the description carries full behavioral burden. The description does not disclose what kind of output is returned (beyond 'candidate API columns'), whether results are ranked, whether multiple candidates can be returned, how resolution handles ambiguity or failure, or whether dataset/cruise_name scoping affects results. For an unannotated tool, this is thin.

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?

Single sentence, front-loaded, no wasted words. It conveys the core operation efficiently, though it is arguably too terse given the need for more behavioral and parameter context.

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 tool has 3 parameters with 0% schema description coverage, no annotations, and an output schema present. The description does not explain the dataset/cruise_name scoping, the resolution process, error/ambiguity handling, or what the output schema represents. For a resolution tool with multiple scoping params and no annotations, the description falls short of what an agent needs to use it correctly.

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%, so the description must compensate for parameter meaning, but it only elaborates on the 'name' parameter (friendly variable name). The 'dataset' and 'cruise_name' parameters are entirely unexplained in the description — their role in scoping the resolution is left to schema titles alone. With 3 parameters and 0% coverage, this is a notable gap, though the description at least frames what 'name' means.

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 states 'Resolve a friendly variable name to candidate API columns,' which has a specific verb (resolve) and resource (friendly variable name → API columns). It communicates the mapping function but doesn't provide detail about what 'friendly' means or what makes columns 'candidate' vs final. It doesn't distinguish itself from siblings, though its purpose seems distinct from the list/get tools.

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 purpose implies a lookup/resolution use case, but there is no explicit statement about when to use this tool versus alternatives. Sibling tools like get_dataset_schema could conceivably provide column info too, and the description doesn't clarify which scenario warrants resolve_variable. No exclusions or alternatives are mentioned.

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