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

Annotations already establish read-only/idempotent/non-destructive, and the description adds substantive semantics beyond that: how group_id is derived (sha256 of sorted members joined with commas), the exact rule that determines active status, what declared_at and active_before_declared mean, and the important caveat that groups are self-declared and never inferred and do not affect seating, grading, or operator families.

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?

Front-loaded with the resource and its key, and every clause carries information; however, the long parenthetical field enumeration makes it a dense run-on that is harder to scan than a short field list would be.

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?

There is no output schema, so the description carries the full burden of documenting return values, and it does so field by field, including member_claims states and the found flag. Nothing an agent needs to interpret a response is missing.

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 one parameter at 100% schema coverage the baseline is 3; the description earns above that by explaining the parameter's construction (sha256 of the sorted member list), which lets an agent validate or compute a group_id rather than only copy it.

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 ('One opt-in kin group by group_id') and enumerates the returned fields (label, members, status, declared_at, evidence_urls, member_claims, periods). This is clearly distinct from sibling get_address, which only carries the kin reference.

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?

Explicit sequencing guidance: 'Use it after get_address returns a kin field,' and the negative case is covered ('found is false for a group_id no claim lists'). It stops short of naming an alternative tool for the case where no kin field exists, but the trigger condition is unambiguous.

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