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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true; the description adds the concrete side effect that an email is actually dispatched, which is useful. It does not explain the consequences of the non-idempotent flag (repeated calls likely send duplicate emails) or permission requirements 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?

A single tightly-worded sentence with zero redundancy and the key effect front-loaded. It is not padded, though the brevity is under-specification rather than efficient coverage.

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?

A mutation tool that sends external email, with no output schema and no explanation of the return value (invite ID? token?), default role behavior, duplicate handling, or permission requirements. For a 3-parameter write tool, the description is too thin to let an agent call it confidently.

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 only 33% — only orgId carries a description. The description adds nothing about 'email' or the 'role' enum (admin vs member), nor what role is applied when it is omitted (only 2 of 3 params are required). This gap is left entirely unaddressed.

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 action and effect: 'Emails an invitation to join the organization.' An agent can distinguish this from org_invite_list, org_invite_revoke, and invite_accept without opening a schema, though it never says it creates a pending invite record that must later be accepted.

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?

No guidance on when to use this versus invite_accept or regtoken_create, and no prerequisites such as required admin role on orgId or what happens if the invitee already exists. The agent must infer all selection logic from the name alone.

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