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

Annotations already declare this is a non-read-only, non-destructive, closed-world mutation; the description adds real behavioral context beyond that, including the free-tier hard block and the mandatory access-check sequence. It does not cover outcomes such as duplicate-admin handling, what invitees receive, or whether the call is idempotent, leaving some gaps for a mutation tool.

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 action and its scope are front-loaded, which is good, but sentences two and three overlap heavily: 'Before offering this action or requesting its inputs, check business permissions' and 'Call check_business_tool_access before collecting inputs' say nearly the same thing. Tightening that redundancy would make the gating sequence read as a single clear sequence.

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 two-parameter tool with a fully described schema, no output schema, and clear annotations, the description covers the critical risks: permission gating, plan-level exclusion, and warning display. What remains unstated are post-call behaviors such as what invited admins receive or how duplicates are handled, which are secondary but would round it out.

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%, with emails described as addresses of the people to add as admins and communityId documented as a Nas.com business ID that must come from list_businesses or another Nas.com tool, never invented. The description adds nothing parameter-specific, so the schema carries the load, but the existing documentation is thorough enough that no compensation is needed.

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: 'Invite or add admin users to a managed community', and clarifies that business and community are interchangeable, which resolves the naming ambiguity against siblings like add_community_admins. It stops short of explicitly saying how it differs from add_community_admins, so an agent must infer they are the same operation under different vocabulary.

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 explicit preconditions and exclusions: check business permissions first, call check_business_tool_access before collecting inputs, FREE businesses cannot use this tool regardless of feature rows, show any grace-period warning and resubscribe link, and never proceed when access is blocked. It names the sibling gate tool directly, which is exactly the routing guidance an agent needs.

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