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

With no annotations present, the description carries the full burden and discharges most of it: it discloses required privilege level per op, that archiving an already-archived org returns `already_archived: true` and performs no mutation, that `trial_ends_at` is null when there is no trial and is pushed by commerce, and that entitlements rows include expired rights plus who set them. Pagination defaults (100, max 500, cursor = previous `next_cursor`) are also spelled out. What is missing is any statement about irreversibility of archive or side effects of create.

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?

Information density is high and almost nothing is wasted, but it is delivered as a single run-on paragraph built from slashes and nested parentheses, which makes the op-to-parameter mapping harder to scan than a per-op line would be. Front-loading 'Manage organizations' is good; the rest would benefit from structure.

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 14-parameter, five-op multiplexed admin tool with no annotations and no output schema, the description is unusually complete: privileges, the already_archived edge case, the trial-field semantics, the entitlements row contents, and the pagination contract are all covered. The residual gap is that no op's return shape is described (there is no output schema to fall back on) and `_org` is undocumented.

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% across 14 parameters, so the description must compensate, and it does for most: `name`, `admin` (with the email|sub|"me"/omitted convention), `org_id`, `right`, `source`, `scope` (all four values glossed in context), `active` (true = valid now, false = expired or not started, omitted = all), `expires_before`, `org_created_after`, `limit`, `cursor`, and `full`. The gaps are `_org`, which is never mentioned, and the fact that param-to-op applicability is only implied by grouping rather than stated.

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 goes well past the bare title: it enumerates all five ops (create, archive, list, get, entitlements) and states the resource each acts on (organizations, org entitlements across the platform). An agent can tell what each op does. It loses the top mark because it never names the adjacent siblings (oto_list_orgs, oto_org, oto_admin_org_member), so the boundary between 'list (all orgs, platform admin)' here and an org-listing tool elsewhere must be inferred.

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?

Each op is paired with the selecting condition and the required privilege: create needs `name` + `admin` and is super admin, archive needs `org_id` and is super admin, list/get/entitlements are platform admin. That is strong when-to-use routing within the tool. It stops short of explicit exclusions or directions to sibling tools when this one is the wrong choice.

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