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

Annotations provide only readOnlyHint=true, and the description adds substantial behavior beyond that: categories are never paged, tags number ~1,600 and are returned ranked by entry count one page at a time, ranking is stable so offset+limit walks without gaps, and an offset past the end yields an empty list rather than an error. It also discloses that matching is not fuzzy and that filters under three letters are ignored. It stops short of describing the response's actual shape, though an output schema exists to cover that.

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?

Purpose comes first, then the usage rule, then paging behavior, then the filter — a well-ordered, front-loaded structure. It is dense with useful detail rather than filler, though "All categories come back whole" is restated in the tag_limit schema description, costing a little redundancy in an otherwise tight passage.

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 four-parameter, read-only listing tool with full schema coverage, an output schema, and readOnlyHint annotations, the description supplies everything an agent needs: when to call it, how paging works, and how filtering behaves. No relevant gap remains for correct invocation.

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 the schema descriptions are themselves detailed, so the baseline would be 3. The description still adds synthesized meaning — why tag_limit/tag_offset exist together (ranking plus paging), that a limit at or above the match count returns everything in one call, and that filter matching is whole-value-substring rather than fuzzy — which is more than a restatement of 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?

States a specific verb and resource ("List the controlled vocabularies") and pins the scope precisely: the domain categories and domain tags that cdc_discover_datasets' category and tags filters are matched against. It explicitly ties itself to a named sibling, so an agent can distinguish it from the other cdc_* tools without reading any 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?

Gives an explicit precondition ("Call it before filtering a search") and the concrete failure mode that justifies it — an unknown value returns an empty page indistinguishable from a valid value with no results. It also names the sibling whose filters it serves and explains the filter parameter's role, leaving nothing to inference.

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