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

Annotations already indicate readOnly, idempotent, and non-destructive behavior, so no contradiction. The description adds crucial behavioral context not visible in the schema: the corpus stores parentage only on the parent's document, so get_family performs a needed inversion. It also discloses the limitation that ancestor-of edges are excluded because they cannot be composed into a generation-by-generation tree. This is exactly the hidden-behavior disclosure an agent needs.

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 front-loaded with the core purpose and then gives only behaviorally important details: the inversion gotcha, the excluded edge type, and where to find alternative data. It is a bit long for a tool description, but every sentence adds decision-relevant value for an agent, so the length is earned rather than padded.

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 has a rich output schema, full parameter coverage, and safety annotations, the description completes the picture by clarifying scope, distinguishing from sibling tools, exposing a critical data-model quirk, and offering fallback slices for excluded data. An agent has enough context to select and invoke this tool correctly without further investigation.

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?

The input schema covers 100% of parameters, so the baseline is 3. The description adds meaningful semantics for the `generations` parameter by explaining it gathers ancestors and descendants one generation at a time, which clarifies the traversal ordering. The `path` usage is reinforced with example like do people/moses and the genealogy question examples map naturally onto parameters.

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 names a clear verb and resource (get a person's family and line of descent) and enumerates the specific relationship types returned: parents, children, siblings, spouses, and optionally ancestors/descendants. It explicitly distinguishes itself from get_entity and from genealogy-related indexes, so an agent can accurately differentiate it among siblings.

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 explicit when-to-use guidance: use it for genealogy, lineage, or ancestry questions, with concrete example queries. It also states when not to rely on it, directing the agent to get_entity for the 680 ancestor-of edges and to themes/genealogy for genealogical passages. This is strong alternative routing.

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