preview_upload

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

No annotations are supplied, so the description must carry the behavioral load; it does disclose the most important trait (a dry run that does not invoke the model) and that counts are computed by code over all rows rather than by a model. It leaves gaps on persistence, any side effects on the supplied files, error behavior, and size limits.

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?

A single dense sentence with the key differentiator ("does not call the model") front-loaded, followed by a parenthetical enumeration of the output. No wasted phrasing, though the packed parenthetical is somewhat list-heavy.

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 only two parameters, no annotations, and no output schema, the description does real work by enumerating the returned content (field names, samples, counts, unique columns, join hints). It falls short only on the purpose parameter and on failure/limit 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 coverage is 100% and both parameters are documented in the schema (files with accepted extensions; purpose as the modeling goal). The description adds only a general sense of what the files become, and says nothing about the purpose parameter's role, so baseline 3 applies.

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 names a specific action ("see what these files would send to the model") and then lists exactly what gets surfaced: field names, sample values, code-computed counts over all rows, per-row-unique columns, and possible joins. The "does not call the model" framing distinguishes it from the model-invoking build path, though no sibling is named explicitly.

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 phrase "does not call the model" implicitly positions this as the safe pre-check before actually building an ontology, but there is no explicit statement of when to prefer it over data_check or data_layout, and no stated prerequisites or exclusions.

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