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

Annotations already cover the safety profile (readOnly, idempotent, non-open-world), so credit goes to genuinely new information: the provenance rule that every returned row names its publisher and that unpublished rows are silently excluded. That is a non-obvious result-set constraint an agent could otherwise misread as 'no fabs exist'. It stops short of describing ordering, paging behavior, or result 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?

Two tight sentences: the searchable dimensions come first, the provenance caveat second. No filler, no restatement of the title, and both sentences carry operational weight.

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?

For a 9-parameter, zero-required search tool with no output schema and partial schema coverage, the definition covers the filtering semantics and one important result-set caveat. The unexplained 'q' free-text parameter and the absent note on ordering/paging are the remaining omissions, but neither blocks a correct first call.

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?

With only 33% schema coverage, the description must compensate, and it largely does by enumerating the filter dimensions (country, operator, kind, status, wafer size, process node) that map to country, operator, type, status, wafer_mm and node. The gap is the free-text 'q' parameter, which appears nowhere in the description, and the 'kind' wording that does not literally match the schema's 'type' key.

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 specific verb ('Search') and resource ('fab sites in the record') and enumerates the filter dimensions, which makes it clearly the discovery/screening tool as opposed to the detail-oriented sibling fab_profile. It does not name any sibling explicitly, so the differentiation is implicit rather than stated.

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 verb 'search' plus the filter list implies the use case (narrow down fabs by attribute), but there is no explicit when-to-use, when-not, or pointer to fab_profile / record_gaps for other tasks. Nothing tells the agent whether to search first and then profile, or what to do if no rows come back.

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