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

With no annotations, the description carries the full burden; it does disclose that create sends email by default and that send_email=false suppresses sending, which is genuinely useful behavior. It omits the consequences of revoke (is the link invalidated? is it reversible?), what happens on duplicate invites for the same email, whether create requires the user to be new, and the response shape for each op.

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?

Very dense and front-loaded: the tool's purpose leads, then a slash-delimited breakdown of each op with its key parameters. The telegraphic style and unexplained tags like "feature cascade, platform tier" cost a little readability but every op clause earns its place.

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 7-parameter, annotation-free, output-schema-less tool, the coverage is reasonable but not sufficient: the document omits `_org`, per-op return values (what create returns when send_email=false), and the effects of revoke. An agent could pick the right op but would still be guessing about results and one parameter.

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 is the only source of meaning, and it does explain op, email, org_id, role (with the org_member|org_admin values), send_email, and invite_id. However, `_org` is left entirely unexplained and no field formats or constraints (e.g., email validation, org_id source) are given, so the compensation is incomplete.

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 users to the oto platform") and enumerates the three modes of operation via op=create/list/revoke, so an agent can tell this is a platform-level invitation manager. The parenthetical "feature cascade, platform tier" is internal jargon that adds little, and it never names the nearby admin siblings (oto_admin_org_member, oto_admin_user) it must not be confused with.

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 clear per-op conditions: omit org_id for pure onboarding, pass org_id plus role to attach directly, send_email=false to get a link instead of a mail, invite_id for revoke, list for pending platform invitations. It stops short of stating when NOT to use it (e.g., adding an existing user to an org should go to oto_admin_org_member) or any prerequisites beyond "Platform admin".

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