Metis · Data Analyst — Record Data Story

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

With no annotations, the description carries the full behavioral burden. It usefully discloses persistence ('attached to the file and returned with it from then on') and a content constraint, but does not say whether stories append or replace, whether the target file must exist, how folder or topic targets behave, or what permissions are required.

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 front-loaded with purpose, followed by concrete usage examples, a critical constraint, and a compact Args block. Every sentence adds useful information, and the structure makes the trigger and restrictions easy to scan.

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 three-parameter mutation tool with no annotations, the description covers the trigger, content constraints, persistence model, and all parameter meanings; the output schema handles return values. It is only slightly incomplete around overwrite/append semantics and folder/topic target behavior.

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 define the parameters, and it does: target can be a file name/path, folder, or topic word; story is the researcher's account in their words; project_id is optional. It does not clarify project_id format or how ambiguous target matches are resolved, but it adds substantial meaning beyond the bare schema.

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 a specific verb and resource: keep/record what the researcher says about a dataset, including origin, quirks, caveats, and history. It clearly distinguishes this from storing row-level data with 'Never put data values from rows in a story,' though it does not explicitly name sibling alternatives such as record_dataset_treatment or register_data_dictionary.

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?

It gives a clear trigger with examples: 'Use whenever they explain a dataset' and parenthetical cases like double-counted districts or lab-join caveats. It also gives a restrictive guideline against including data values, but does not explicitly say when to prefer another tool or what to do if the explanation is not dataset-specific.

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