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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description only needs to add operational context. It does add two useful facts — a 100-row result cap and the API-key requirement — but the key requirement is largely duplicated by the api_key schema field, and 'light rows' is unexplained jargon rather than a real disclosure of return shape.

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 compact, front-loaded sentences with no filler; the core capability leads and the constraints follow. Slightly terse to the point of relying on abbreviations ('scope us|all', 'light rows') that compress meaning at the cost of clarity.

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 does state the return cap and auth need, which is the right instinct for a 7-param search tool. But it leaves out pagination/ordering behavior, how filters combine, what 'scored' means, and any differentiation from sibling data tools, so it is only minimally sufficient.

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 57%, and the description groups the filters (industries, states, score range, scope us|all), which usefully names the otherwise-undocumented scoreMin/scoreMax pair. It adds no format, range, or semantics detail beyond that grouping, and omits limit and api_key entirely.

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?

States a clear verb+resource (query the scored company dataset) and enumerates the filter dimensions, so an agent knows exactly what it does. However, it never distinguishes itself from close siblings like dataset_sample or data_records, which could easily serve as alternatives for the same dataset.

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 choose this tool over dataset_sample, data_records, or the aeo_* siblings, and no explanation of when a filtered search is appropriate. The only usage-adjacent content is a hard precondition (API key required), not a use/when-not rule.

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