dna

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

Despite minimal annotations (readOnlyHint=false, destructiveHint=false), the description provides substantial behavioral details. It clarifies what each action does: tests require testGuid, matches includes filters and sort, add_to_group/remove_from_group modifies group memberships, set_note explicitly says 'empty clears', match_detail returns shared cM/segments and predicted relationship, and ethnicity gives estimate regions. This goes beyond the schema by explaining side effects and output content, though it omits persistence and error behavior.

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?

The description is extremely dense, packing nearly all tool information into a single run-on paragraph. Every piece of information is relevant, but the lack of line breaks or bullet points makes it hard to parse. It front-loads 'AncestryDNA' but then presents a lengthy stream of actions and filters. It is more a reference manual than a concise summary, though it avoids fluff.

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?

Given the tool's complexity (19 parameters, 8 actions, no output schema) and sparse annotations, the description is incomplete. It hints at outputs for match_detail and ethnicity, but not for matches, groups, or mutations. It does not explain prerequisites like needing a testGuid before querying matches, pagination semantics for page, or what fields are returned. An agent would need to infer many calling conventions, making this below the minimum viable completeness for such a multi-action 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?

With 0% schema description coverage, the description carries the burden of explaining parameters. It does well by mapping filters to actions: minCm/maxCm, parentalSide enumerations, trees, groupIds ('2 = starred'), nameSearch, sortBy values, pageSize limit, and sharedWithMatchGuid semantics. It also notes action-specific required parameters like matchGuids+groupId for add/remove. However, a few parameters (page, matchGuid) are not explicitly tied to actions, so compensation is not complete.

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 description clearly indicates the tool covers AncestryDNA functionality and enumerates all actions: tests, matches, groups, add/remove group, match detail, set note, ethnicity. This is specific enough to distinguish from sibling tools like tree, person, or search_records, which focus on other genealogy data. However, it lacks a single crisp verb phrase summarizing the tool's overall purpose, instead presenting a list of sub-actions.

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 description gives no explicit guidance on when to choose this tool over siblings. It implies AncestryDNA-related use by naming DNA-specific actions and filters, but it does not state any criteria or exclusions. There is no mention of alternatives, prerequisites, or scenarios where another tool would be more appropriate, leaving the agent to infer.

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