Preview Resource

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

With no annotations, the description carries the full burden, and it does disclose real behavioral traits: a cost/side-effect profile (free for portal DataStore resources, otherwise it downloads and caches the file and makes the follow-up query free). It still omits permissions/auth requirements, whether the caching is durable across sessions, and failure modes for missing resource_id.

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 short sentences, each earning its place: one defines output, one defines the call ordering requirement, one explains cost. The prerequisite is front-loaded rather than buried at the end.

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?

An output schema exists, so return values need not be explained, and the description still summarizes them usefully. It covers the prerequisite, the cost model, and the caching side effect, leaving only auth/permission context and error behavior unaddressed — modest gaps for an otherwise well-specified read-with-caching tool.

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%, so resource_id, limit, and portal are already documented in the schema; the baseline is 3. The description only alludes to the sample size implicitly ('a sample of rows') and adds no formatting or portal-selection guidance beyond the 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 first sentence names a specific verb plus the exact payload the agent gets back: columns, column types, sample rows, and total row count. That is enough to separate it from get_dataset (metadata) and query_resource (SQL execution) without opening either schema.

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 states an explicit prerequisite ('ALWAYS call this before query_resource') and gives the reason ('you cannot write correct SQL without first seeing the column names'), which is precisely the routing decision an agent needs. The alternative tool is named and the condition that triggers this one is unambiguous.

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