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

Beyond the annotations, the description discloses that an invitation email is sent, that a join link is returned, and that non-admin roles are rejected. It also lists concrete failure conditions such as existing membership, pending invites, and hitting the member limit. This matches the readOnlyHint=false and openWorldHint=true annotations without contradiction.

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 dense but every clause carries useful information: core action, return value, authorization, role constraints, failure modes, and tenant targeting. It is front-loaded with the main behavior and does not include filler or redundant material beyond acceptable reinforcement.

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 an output schema available, the return value structure is already specified, and the description still covers the join-link return, authorization requirements, role constraints, failure conditions, and the active-tenant dependency. An agent has enough context to invoke the tool correctly and handle expected errors.

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 100%, and the schema already documents role defaults and meanings. The tool description adds the 'cannot invite as owner' constraint and some email-related failure conditions, but it largely restates what the input schema already provides, so it adds only marginal semantic value.

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 opens with a specific verb-resource pair: 'Invite someone to the active team (tenant) by email.' It also clarifies the outcome by stating that an invitation email is sent and the join link is returned. This clearly separates it from team-scoping siblings like list_my_tenants and switch_active_tenant by noting it operates on the active tenant.

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 explicitly states who may invoke the tool: only the team owner or an admin, with rejection for other roles. It also tells the agent to use list_my_tenants or switch_active_tenant first if a different team is intended, which is direct usage guidance and alternative routing.

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