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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds material behavior: signed URLs expire in one hour, payloads must not be pasted into the conversation, and all arguments except dataset fall back to a free preview requiring no API key. It stops short of stating whether handles can be re-requested cheaply or whether any quota applies.

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?

Front-loaded with the key distinction ("not the data"), then the payload contents, then the usage constraint and the fallback tool. Three dense sentences with no filler; the enumerated return contents earn their space because no output schema exists.

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 no output schema, the description correctly carries the burden of explaining return values and does so thoroughly, plus the never-paste and no-API-key constraints. Remaining gaps are minor: no note on size/row limits, error behavior, or what happens when a handle's URLs lapse.

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%, so the baseline is 3, but the description adds real meaning: every argument other than dataset resolves to the free preview, and that preview needs no API key. That clarifies the defaulting behavior and its access implications in a way the schema alone does not.

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?

"A handle to one slice of a dataset, not the data" is a precise verb+resource statement that immediately separates this from a tool that returns data itself, and it enumerates exactly what the handle contains (signed Parquet URLs, schema, row counts, column stats, samples, snippet). It also explicitly names the sibling (summarize) it is not to be confused with.

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?

Gives clear when-to-use context ("Load the files in your own code; never paste them into the conversation") and names one alternative with its selection condition ("Without code, use summarize"). It does not differentiate against the other plausible siblings, fetch and describe_dataset, so the routing picture is incomplete.

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