Manage Variables & Datasets

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write profile is covered. The description usefully adds that CSV headers auto-bind to matching object names and that it runs in background mode without invoking Computer Use, but it never warns that create/apply/bind actions mutate the document.

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?

Three sentences, front-loaded with the operation list and no filler. The execution-mode note is placed last where it belongs, though the opening list slightly duplicates the action enum.

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 an eight-action multiplexer with no output schema, the description maps only the main operations and leaves 'export' unmentioned and per-action prerequisites unstated. Annotations carry the safety profile, but the agent gets only a partial action map.

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 100% and the 'dataset_name_prefix' note ('If omitted, first column value is used') already lives in the schema. The description's CSV auto-binding sentence adds marginal value but mostly restates schema-level behavior, so a baseline 3 fits.

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 specific verbs and resources ('List variables/datasets, apply or create datasets, bind variables to objects, import CSV/XML'), so the domain is unmistakable. It covers most of the action enum but omits 'export', and it does not distinguish itself from overlapping siblings like 'export'/'import' by name.

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?

There is no when-to-use guidance and no exclusions. With sibling tools literally named 'export' and 'import' that overlap with this tool's import/export actions, the agent receives no help deciding which entry point to pick.

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