Metis · Data Analyst — Data Memory Dataset

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

No annotations are present, so the description carries the full burden. 'Everything known about one data file' implies a non-destructive lookup and the content list hints at the return shape, but it says nothing about prerequisites (does the file need to be tracked/scanned first?) or what happens when the file is unknown or ambiguous.

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?

Two compact blocks, with the summary line front-loaded before the argument note. The 'Args:' formatting is slightly code-flavored but wastes no words.

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?

With one parameter and an output schema present, the description needn't explain return values, and it correctly covers the input format. However, for a lookup tool embedded in a dense family of data_memory_* siblings, the absence of prerequisite and disambiguation guidance leaves a meaningful gap.

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 parameter documentation in the description is doing real work: it specifies that name_or_path accepts either a bare file name (with example 'survey_results.xlsx') or a full path. What is missing is path-resolution behavior, e.g. relative to which root, and how duplicate names are handled.

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 the resource precisely ('one data file') and enumerates the content returned (paths, readers, writers, columns, values, stories), which makes the tool's output distinctly recognizable. It does not state a verb ('retrieve/get') nor distinguish itself from close siblings such as data_memory, data_memory_scan, or data_memory_status.

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 guidance on when to call this versus data_memory, data_memory_scan, or data_memory_status. The only scoping hint is 'one data file', which an agent must infer as the single-dataset counterpart of the broader memory tools.

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