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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description adds real behavioral context: results are 'bounded', raw claims and evidence are opt-in, and access is permission-gated ('excluded unless a future explicit permission adds this surface'). It doesn't disclose pagination or default return shape, keeping it out of the top tier.

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?

It is a single dense sentence with nested parentheticals and a mid-sentence colon example, front-loaded with the core verb but heavy to parse. No outright waste, yet the run-on construction hurts readability.

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 and 0% schema coverage across 6 parameters, the description should do more. It covers purpose, ownership semantics, and permission gating well, but omits any explanation of the parameters or the returned claim structure an agent needs to call it correctly.

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 description coverage is 0%, so the description carries the param burden. It hints at includeRawClaims/includeEvidence ('optional raw claims and evidence'), scope ('member or household'), and limit ('bounded'), but leaves clientId, memberIds, and actual limit bounds entirely undocumented. Partial compensation only.

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 states a specific verb ('Return') and resource ('bounded business-entity graph claims for a member or household'), and elaborates on a distinctive output, effectiveOwnership look-through with a concrete example. This clearly separates it from generic context tools, though it never names a specific sibling like get_professional_graph_context or list_household_entities.

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?

It provides an implied usage goal ('so you can answer what they effectively own through their entities') and notes an exclusion ('Scoped specialists are excluded'), but gives no explicit when-to-use versus alternatives or prerequisites for choosing this over list_household_entities or get_family_office_context. Usage is inferable rather than directed.

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